INDEX

Explanations

references to different social roles and groups within the community

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

 Films

-0.15

icos

-0.15

ute

-0.14

Ð»Ð¸Ñı

-0.14

tim

-0.14

 putchar

-0.14

arms

-0.14

alue

-0.14

ffffffff

-0.14

ocol

-0.14

POSITIVE LOGITS

'gc

0.16

æ»

0.15

rahim

0.14

_cre

0.14

REEN

0.14

ç¢¼

0.14

/kernel

0.14

 Blasio

0.14

_fu

0.14

riba

0.14

Activations Density 0.169%

references to different social roles and groups within the community

No Comments

No Known Activations