INDEX

Explanations

instances of film-related information and mentions of specific celebrities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

bsub

-0.17

 Blasio

-0.15

ugin

-0.15

ÃŃcio

-0.15

ohon

-0.14

 Liberation

-0.14

 Pearce

-0.14

Î±Î½Î¬

-0.14

olian

-0.14

ector

-0.14

POSITIVE LOGITS

 Werner

0.15

ivy

0.15

 armour

0.15

éŀĭ

0.15

elper

0.14

iali

0.14

áº¡n

0.14

chen

0.14

eft

0.14

vil

0.14

Activations Density 0.111%

instances of film-related information and mentions of specific celebrities

No Comments

No Known Activations