INDEX

Explanations

introductory phrases that clarify or contextualize statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

kÃ¶

-0.17

Î±Î½Î¬

-0.14

jong

-0.14

apos

-0.14

(::

-0.14

vp

-0.13

auled

-0.13

cog

-0.13

Sk

-0.13

ATABASE

-0.13

POSITIVE LOGITS

idan

0.18

ensa

0.17

enson

0.15

ews

0.15

fono

0.15

æŁ³

0.14

ÐµÐºÐ¾

0.14

ÑĥÑĩÐ°

0.14

 disclaimer

0.14

srp

0.14

Activations Density 0.059%

introductory phrases that clarify or contextualize statements

No Comments

No Known Activations