INDEX

Explanations

expressions related to effort and pushing boundaries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

asily

-0.15

Ð¶Ñĥ

-0.15

_oid

-0.14

ERC

-0.14

cona

-0.14

cken

-0.14

_lineno

-0.13

Ã§Ä±

-0.13

erna

-0.13

zon

-0.13

POSITIVE LOGITS

0.17

esc

0.16

ToFront

0.16

erte

0.14

ivation

0.14

(push

0.14

FileDialog

0.13

 towards

0.13

-through

0.13

/embed

0.13

Activations Density 0.041%

expressions related to effort and pushing boundaries

No Comments

No Known Activations