INDEX

Explanations

instances of the word "before" in various contexts, indicating the concept of prior action or condition

oai_token-act-pair · gpt-4o-mini Triggered 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

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 tier

-0.16

Î®ÏĤ

-0.15

lad

-0.15

/me

-0.15

phin

-0.15

ave

-0.14

 recuper

-0.14

Lad

-0.14

POSITIVE LOGITS

ensch

0.16

_FOREACH

0.16

Å¾enÃŃ

0.15

vÄĽd

0.15

ÅĻad

0.15

liÅ¡

0.14

-inverse

0.14

ansÄ±

0.14

icode

0.14

fÃ©

0.14

Activations Density 0.028%

instances of the word "before" in various contexts, indicating the concept of prior action or condition

No Comments

No Known Activations