© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 22-LLAMASCOPE-RES-32K
    11. 19369
    Prev
    Next
    INDEX
    Explanations

    the pronoun "we" along with modal and conditional verbs that express ability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jak
    -0.18
    jah
    -0.14
    idge
    -0.14
    Location
    -0.14
    sembles
    -0.14
    WI
    -0.14
    ELY
    -0.14
    hos
    -0.14
     Bowman
    -0.14
    jaw
    -0.14
    POSITIVE LOGITS
    sterol
    0.15
    alo
    0.15
     bergen
    0.15
    ProcessEvent
    0.15
     Berg
    0.14
    aul
    0.14
    lene
    0.14
    łĢ
    0.14
    })();↵↵
    0.14
    krom
    0.14
    Activations Density 0.002%

    No Known Activations