INDEX

Explanations

references to coding tools or environments

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

anter

-0.17

Ã³j

-0.16

anst

-0.15

avern

-0.15

 Davies

-0.15

unders

-0.14

Go

-0.14

ensis

-0.14

ens

-0.14

ØŃ

-0.14

POSITIVE LOGITS

IDL

0.15

uforia

0.15

:\/\/

0.15

ults

0.15

orado

0.15

alat

0.14

\Traits

0.14

è³

0.14

utzer

0.14

 xmlhttp

0.14

Activations Density 0.000%

references to coding tools or environments

No Comments

No Known Activations