INDEX

Explanations

periods or full stops 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 @ 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

ael

-0.16

ingham

-0.15

Ã¥

-0.15

inds

-0.15

amoto

-0.14

ington

-0.14

ellen

-0.14

quil

-0.14

es

-0.14

alist

-0.14

POSITIVE LOGITS

vore

0.15

UTTON

0.14

ylland

0.14

Ecc

0.14

TPL

0.14

å·§

0.13

ÑĢÑĸÑĩ

0.13

è³Ģ

0.13

ownt

0.13

mÃ¼r

0.13

Activations Density 0.066%

periods or full stops in the text

No Comments

No Known Activations