INDEX

Explanations

the word "also" and its variations, indicating a focus on inclusivity or additional information

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

aversable

-0.16

oller

-0.16

éº

-0.15

ä¸īçº§

-0.15

 ÐºÐ¾Ð¼

-0.15

_marshall

-0.15

asma

-0.14

atta

-0.14

marshal

-0.14

arem

-0.14

POSITIVE LOGITS

 Grove

0.17

ordes

0.16

otle

0.15

 èį

0.15

Ã¨ve

0.14

 ØªÙĥ

0.14

obao

0.14

 Guth

0.14

HG

0.14

Activations Density 0.069%

the word "also" and its variations, indicating a focus on inclusivity or additional information

No Comments

No Known Activations