INDEX

Explanations

mentions of voluntary actions or programs

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

lej

-0.17

 crossorigin

-0.17

ween

-0.16

ODULE

-0.15

ilde

-0.15

AccessType

-0.14

ÑĩÐ¸Ð²

-0.14

ÙĦÛĮØ³ÛĮ

-0.14

ÑĩÐ°ÑĤ

-0.14

 Spread

-0.14

POSITIVE LOGITS

venta

0.15

aly

0.15

idth

0.15

unts

0.14

iste

0.14

lete

0.14

addin

0.14

andle

0.14

amt

0.14

ately

0.14

Activations Density 0.029%

mentions of voluntary actions or programs

No Comments

No Known Activations