INDEX

Explanations

references to time and frequency regarding actions or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

Ø§Ø±Ø¨

-0.15

-caption

-0.15

 proverb

-0.14

 perpet

-0.14

athers

-0.14

ami

-0.14

ãģĸ

-0.14

ekil

-0.14

fers

-0.14

\OptionsResolver

-0.13

POSITIVE LOGITS

oeff

0.17

empo

0.16

rud

0.16

added

0.16

(optional

0.16

ÏĢÎ¿Î½

0.15

 additional

0.14

MUX

0.14

 adding

0.14

Ð´Ñı

0.14

Activations Density 0.198%

references to time and frequency regarding actions or events

No Comments

No Known Activations