INDEX

Explanations

punctuation and symbols in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

Ã¶l

-0.18

lero

-0.15

azo

-0.15

Ð°Ð½Ðº

-0.15

yne

-0.15

/Area

-0.15

_SHADOW

-0.15

íĶ

-0.14

agraph

-0.14

ÐµÐ»ÐµÑĦÐ¾Ð½

-0.14

POSITIVE LOGITS

wich

0.16

ofi

0.16

aiser

0.15

 Imag

0.15

im

0.15

0.14

entina

0.14

Ã³d

0.14

of

0.14

Activations Density 0.000%

punctuation and symbols in the text

No Comments

No Known Activations