INDEX

Explanations

phrases or references to social media interactions

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

ais

-0.14

ĨĴ

-0.14

 Forrest

-0.14

bum

-0.13

oul

-0.13

acin

-0.13

ask

-0.13

ohl

-0.13

.imp

-0.13

alue

-0.13

POSITIVE LOGITS

Xia

0.19

quot

0.15

riel

0.14

rzy

0.14

utto

0.14

ÙĪÛĮØ¯

0.14

0.13

conds

0.13

Uvs

0.13

ivet

0.13

Activations Density 0.003%

phrases or references to social media interactions

No Comments

No Known Activations