INDEX

Explanations

references to characters or elements from pop culture

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 Freak

-0.16

èĥĮ

-0.15

rette

-0.15

 Jacobs

-0.14

 Jacob

-0.14

ãĤ¿ãĤ¤

-0.14

å°½

-0.14

oso

-0.14

ActionButton

-0.14

_misc

-0.14

POSITIVE LOGITS

 Severity

0.15

/stdc

0.15

Ã¡h

0.14

 trainable

0.14

Äįi

0.14

kke

0.13

wanted

0.13

 dolu

0.13

Ã¡bado

0.13

Activations Density 0.043%

references to characters or elements from pop culture

No Comments

No Known Activations