INDEX

Explanations

references to file paths and user directories

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ç§

-0.15

loe

-0.14

ins

-0.14

 Arabian

-0.13

Eye

-0.13

antino

-0.13

hoe

-0.13

IRC

-0.13

 counsel

-0.13

 reprodu

-0.13

POSITIVE LOGITS

ruÅ¾

0.15

anness

0.14

 Bull

0.14

mission

0.13

_VISIBLE

0.13

 millenn

0.13

 phÃ³ng

0.13

idges

0.13

ocs

0.13

chu

0.13

Activations Density 0.007%

references to file paths and user directories

No Comments

No Known Activations