INDEX

Explanations

patterns of punctuation and formatting in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ias

-0.15

-0.14

-0.13

stan

-0.13

 rend

-0.13

 which

-0.13

.cmd

-0.13

Ãª

-0.13

POSITIVE LOGITS

 dafÃ¼r

0.17

rlen

0.16

usat

0.16

Bulk

0.15

ÏĦÎ±ÏĤ

0.15

ÙĪÙĨØ§

0.15

0.14

å§ĳ

0.14

asjon

0.14

 ekip

0.14

Activations Density 0.070%

patterns of punctuation and formatting in text

No Comments

No Known Activations

patterns of punctuation and formatting in text

No Comments

No Known Activations