INDEX

Explanations

references to activism and advocacy efforts

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

lif

-0.16

itas

-0.15

gaard

-0.15

ÅĻiv

-0.14

ickle

-0.14

elles

-0.14

Î»ÎŃ

-0.14

uchos

-0.13

 sáºµn

-0.13

agal

-0.13

POSITIVE LOGITS

argin

0.16

shint

0.15

 Influence

0.15

istung

0.15

Łèĥ½

0.14

sten

0.14

(EFFECT

0.14

 Lowest

0.14

ÐµÑĢÐ¶Ð°Ð²

0.14

arin

0.14

Activations Density 0.341%

references to activism and advocacy efforts

No Comments

No Known Activations