© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 6-LLAMASCOPE-RES-32K
    6. 25038
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and emotions

    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
    á»ĥ
    -0.16
    983
    -0.15
    ouver
    -0.15
    hots
    -0.15
    vey
    -0.14
    972
    -0.14
    ancellor
    -0.14
    982
    -0.14
    629
    -0.14
    illez
    -0.14
    POSITIVE LOGITS
    izza
    0.14
    ackers
    0.13
    phia
    0.13
     Dod
    0.13
    ulo
    0.13
    vro
    0.13
    å½±åĵį
    0.13
    ÙĬار
    0.13
    iddi
    0.13
    ½
    0.12
    Activations Density 0.058%

    No Known Activations