INDEX

Explanations

references to measurements or quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ismic

-0.17

erno

-0.17

Ø±

-0.14

inders

-0.14

stras

-0.14

atsby

-0.14

stre

-0.14

Ã¡lie

-0.14

adlo

-0.14

ÅĻi

-0.14

POSITIVE LOGITS

reg

0.15

oler

0.15

ler

0.14

 whom

0.14

ref

0.14

PageRoute

0.14

Ø³Ø¯

0.14

à¥į

0.13

outh

0.13

Activations Density 0.013%

references to measurements or quantities

No Comments

No Known Activations