INDEX

Explanations

references to academic journals and publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ods

-0.17

essed

-0.15

 tele

-0.14

 York

-0.14

 Suns

-0.14

ÑĹÑħ

-0.14

iska

-0.13

 æ®

-0.13

pl

-0.13

ud

-0.13

POSITIVE LOGITS

èªĮ

0.21

azine

0.20

bsub

0.17

 magazine

0.16

 Ð¶ÑĥÑĢÐ½

0.16

ÙĲØ±

0.15

.printf

0.15

 journal

0.15

istes

0.15

Ð¾ÑĢÐ¾Ð½Ð¸

0.15

Activations Density 0.054%

references to academic journals and publications

No Comments

No Known Activations