INDEX

Explanations

references to authorship and the act of writing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

uko

-0.14

ãĥªãĤ¢

-0.14

agram

-0.14

ãģĹãģ®

-0.14

æīį

-0.14

decess

-0.14

 Benson

-0.14

ovan

-0.13

æīįèĥ½

-0.13

agg

-0.13

POSITIVE LOGITS

ondo

0.15

ÑĸÐ³

0.14

InputDialog

0.14

_intf

0.14

 okol

0.14

VisualStyle

0.14

ulen

0.14

olson

0.13

zbollah

0.13

essen

0.13

Activations Density 0.176%

references to authorship and the act of writing

No Comments

No Known Activations