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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 6-LLAMASCOPE-RES-32K
    11. 6820
    Prev
    Next
    INDEX
    Explanations

    phrases related to "off" or "offsite" concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ร
    -0.19
    anki
    -0.17
    lint
    -0.16
     پرد
    -0.16
    ufig
    -0.15
    ccione
    -0.15
    ERSHEY
    -0.15
    ontology
    -0.15
    aters
    -0.15
    ovsky
    -0.15
    POSITIVE LOGITS
    ensively
    0.23
    /on
    0.16
    oll
    0.16
    ischer
    0.16
    wards
    0.16
     Trot
    0.15
    entimes
    0.15
    ord
    0.15
    /off
    0.15
    VPN
    0.15
    Activations Density 0.060%

    No Known Activations