INDEX

Explanations

references to specific data projects or repository identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.16

atz

-0.16

quals

-0.15

CORD

-0.15

-0.14

erais

-0.14

inecraft

-0.14

 theories

-0.14

iyat

-0.13

omnia

-0.13

POSITIVE LOGITS

psz

0.17

ëĭ´

0.15

elop

0.15

allen

0.14

ron

0.14

RELATED

0.14

stay

0.14

imi

0.13

iger

0.13

own

0.13

Activations Density 0.034%

references to specific data projects or repository identifiers

No Comments

No Known Activations