© 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. 26-LLAMASCOPE-RES-32K
    6. 1254
    Prev
    Next
    INDEX
    Explanations

    themes related to interpersonal relationships and family dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Äįet
    -0.17
     cousin
    -0.15
    Ä
    -0.15
    preg
    -0.15
    815
    -0.14
     Cousins
    -0.14
    辦
    -0.14
     pregnant
    -0.14
     Uncle
    -0.14
     preg
    -0.14
    POSITIVE LOGITS
     helicopt
    0.22
     helicopter
    0.22
     role
    0.21
     absentee
    0.21
     raising
    0.20
     modeling
    0.20
     roles
    0.20
    è§Ĵèī²
    0.18
    æ¦ľ
    0.18
     raised
    0.18
    Activations Density 0.091%

    No Known Activations