INDEX

Explanations

instances of sharing or communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

Ã½

-0.14

antas

-0.14

Parms

-0.13

enga

-0.13

enge

-0.13

Proceed

-0.13

MOM

-0.13

Ģ

-0.13

áº©n

-0.13

POSITIVE LOGITS

ayÄ±m

0.14

NgModule

0.14

sharing

0.14

atre

0.13

resher

0.13

acades

0.13

uilder

0.13

polator

0.13

DBNull

0.13

ampo

0.13

Activations Density 0.099%

instances of sharing or communication

No Comments

No Known Activations