INDEX

Explanations

references to specific subjects or categories, particularly in instructional or descriptive contexts

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

inish

-0.17

 gravity

-0.15

prech

-0.15

ÑĦÐ¸

-0.15

 Tone

-0.14

 Bullet

-0.14

ajo

-0.13

uitka

-0.13

ÙģØ§ÙĦ

-0.13

POSITIVE LOGITS

-package

0.16

ap

0.14

CJK

0.14

ÅĻÃŃÅ¾

0.14

è¹

0.14

ended

0.14

Ĵ

0.13

åĿĬ

0.13

 satur

0.13

ìĭŃìĭľìĺ¤

0.13

Activations Density 0.007%

references to specific subjects or categories, particularly in instructional or descriptive contexts

No Comments

No Known Activations