INDEX

Explanations

references to specific ideas, themes, and goals articulated in the text

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

.'/'.$

-0.17

onz

-0.16

agas

-0.15

ETY

-0.15

tery

-0.14

OVÃģ

-0.14

ÙģØ§ÙĤ

-0.14

Ø§Ø¦Ùģ

-0.14

loop

-0.13

burgh

-0.13

POSITIVE LOGITS

Ĳľ

0.16

 foss

0.14

ÅĻe

0.14

å¾Ĵ

0.14

ollapsed

0.14

,readonly

0.14

'gc

0.14

oir

0.14

 grou

0.14

Ã©rÃ©

0.13

Activations Density 0.833%

references to specific ideas, themes, and goals articulated in the text

No Comments

No Known Activations