INDEX

Explanations

specific names or unique identifiers in the text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

áº©u

-0.15

["@

-0.13

indir

-0.13

porto

-0.13

Äįet

-0.13

Î¯Î½

-0.12

ãĥªãĥ³ãĤ¯

-0.12

 Crosby

-0.12

 vitamins

-0.12

@Spring

-0.12

POSITIVE LOGITS

 embodied

0.22

 situated

0.19

lay

0.19

 Actor

0.18

 actor

0.17

 arte

0.17

 particip

0.17

('

0.17

 Everyday

0.16

 everyday

0.16

Activations Density 0.016%

specific names or unique identifiers in the text

No Comments

No Known Activations