INDEX

Explanations

punctuation marks and their variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ration

-0.14

oker

-0.14

_svg

-0.14

à¤¹à¤¨

-0.14

.transparent

-0.14

 Constantin

-0.14

bons

-0.14

izyon

-0.13

inds

-0.13

itos

-0.13

POSITIVE LOGITS

à¤Ŀ

0.15

utex

0.15

IVEN

0.15

upal

0.15

usercontent

0.15

å³°

0.15

0.14

Î¼ÏĨ

0.14

oÄį

0.14

Lim

0.13

Activations Density 0.040%

punctuation marks and their variations

No Comments

No Known Activations