INDEX

Explanations

instances of the word "force" in various contexts

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

ilter

-0.16

perPage

-0.15

etheus

-0.15

ingu

-0.15

raphic

-0.15

jsc

-0.14

laÅŁ

-0.14

raman

-0.14

lik

-0.14

embr

-0.14

POSITIVE LOGITS

ful

0.46

fulness

0.35

ps

0.34

field

0.34

FUL

0.29

fully

0.29

 multiplier

0.28

fields

0.27

-field

0.25

FIELD

0.24

Activations Density 0.034%

instances of the word "force" in various contexts

No Comments

No Known Activations