© 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. 17-LLAMASCOPE-RES-32K
    6. 22559
    Prev
    Next
    INDEX
    Explanations

    prepositions and words of spatial or relational significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xis
    -0.15
    ener
    -0.14
    apro
    -0.14
    abin
    -0.14
     hell
    -0.13
    emp
    -0.13
    herits
    -0.13
     Constructors
    -0.13
    asi
    -0.13
    instanc
    -0.13
    POSITIVE LOGITS
    ERGY
    0.16
    EXTERN
    0.14
    ÙĪÙĩ
    0.14
    ÐIJÑĢÑħÑĸв
    0.14
    .geo
    0.14
    रल
    0.13
    олаг
    0.13
    isphere
    0.13
    оÑĢалÑĮ
    0.13
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.13
    Activations Density 0.010%

    No Known Activations