INDEX

Explanations

proper nouns and specific references to locations or entities

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

acro

-0.14

yon

-0.14

Of

-0.14

rod

-0.14

ION

-0.14

-of

-0.13

ÙħÙĨ

-0.13

ion

-0.13

ace

-0.13

POSITIVE LOGITS

aug

0.17

NetMessage

0.16

ernet

0.16

chester

0.15

urd

0.15

spath

0.14

ools

0.14

itia

0.14

orno

0.14

erie

0.14

Activations Density 0.140%

proper nouns and specific references to locations or entities

No Comments

No Known Activations