INDEX

Explanations

references to various forms of media and entertainment

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

zan

-0.15

avian

-0.14

Hint

-0.14

Jeremy

-0.14

II

-0.13

DH

-0.13

vek

-0.13

avn

-0.13

feld

-0.13

ÙĥØ³

-0.13

POSITIVE LOGITS

atha

0.18

lettes

0.17

ellas

0.16

ÅĻi

0.16

 Uncategorized

0.15

ÑĢÑıÐ´

0.14

ripp

0.14

addir

0.14

nave

0.14

-pill

0.14

Activations Density 0.087%

references to various forms of media and entertainment

No Comments

No Known Activations