INDEX

Explanations

phrases indicating choices and decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

inge

-0.16

ahas

-0.15

endra

-0.15

trie

-0.15

stag

-0.15

ader

-0.15

adera

-0.14

dst

-0.14

dre

-0.14

ivil

-0.14

POSITIVE LOGITS

CurrentValue

0.15

Ã¼gen

0.15

avicon

0.14

quam

0.14

Pap

0.14

 Guinea

0.14

ĻĤ

0.14

0.13

getField

0.13

Activations Density 0.015%

phrases indicating choices and decisions

No Comments

No Known Activations