INDEX

Explanations

references to common occurrences or issues in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

isser

-0.16

uren

-0.16

dea

-0.15

ister

-0.15

avl

-0.15

thren

-0.14

uw

-0.14

egan

-0.14

meer

-0.14

amas

-0.14

POSITIVE LOGITS

 among

0.19

 amongst

0.19

 encountered

0.19

-used

0.18

 xuyÃªn

0.17

among

0.17

 found

0.17

 ÑģÑĢÐµÐ´Ð¸

0.16

 heard

0.15

 Asked

0.15

Activations Density 0.138%

references to common occurrences or issues in various contexts

No Comments

No Known Activations