INDEX

Explanations

references to data input and processing functions in code

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

ponse

-0.15

rouch

-0.14

ANTE

-0.14

ãĥ¬ãĥĵ

-0.14

 Taylor

-0.14

visor

-0.14

 Falk

-0.14

Tet

-0.14

ArrayType

-0.14

otify

-0.14

POSITIVE LOGITS

 Patch

0.15

uell

0.15

 PATCH

0.14

ureka

0.14

 patch

0.14

ago

0.14

\Eloquent

0.14

smart

0.14

alama

0.14

Millis

0.14

Activations Density 0.050%

references to data input and processing functions in code

No Comments

No Known Activations