© 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. 24-LLAMASCOPE-RES-32K
    6. 8154
    Prev
    Next
    INDEX
    Explanations

    statements related to wildlife conservation and management challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĵľ
    -0.15
     bench
    -0.14
     chickens
    -0.14
    unker
    -0.14
    åıĺ
    -0.14
     poultry
    -0.14
     waterfront
    -0.14
     coma
    -0.13
    userdata
    -0.13
     jungle
    -0.13
    POSITIVE LOGITS
     populations
    0.38
     population
    0.38
     Population
    0.33
    population
    0.31
    Population
    0.30
     reint
    0.26
    .population
    0.24
     extinction
    0.23
    _population
    0.23
     threatened
    0.22
    Activations Density 0.183%

    No Known Activations