INDEX

Explanations

references to test files or test-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

mlink

-0.16

orm

-0.15

rib

-0.15

ãģĵãģĨ

-0.14

Ne

-0.14

 constitution

-0.14

box

-0.14

urs

-0.14

POSITIVE LOGITS

ouro

0.18

ossal

0.17

 HÃ¼s

0.15

IPH

0.15

ÐŁÐļ

0.15

jf

0.15

tember

0.15

DDS

0.15

ibold

0.15

myModal

0.15

Activations Density 0.036%

references to test files or test-related terms

No Comments

No Known Activations