INDEX

Explanations

references to potential clients or candidates 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 @ 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

Ã¤tz

-0.14

immel

-0.14

umm

-0.14

amine

-0.14

gow

-0.14

halt

-0.14

ETING

-0.13

verity

-0.13

hi

-0.13

omet

-0.13

POSITIVE LOGITS

/current

0.17

sWith

0.15

clave

0.14

 moÅ¾

0.14

roud

0.14

 wiÄĻc

0.13

aille

0.13

arker

0.13

Activations Density 0.047%

references to potential clients or candidates in various contexts

No Comments

No Known Activations