INDEX

Explanations

mentions of tags and categories within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

YPE

-0.14

uy

-0.14

verage

-0.14

_ln

-0.13

reo

-0.13

 Rencontres

-0.13

oin

-0.13

(::

-0.13

ln

-0.12

 Holl

-0.12

POSITIVE LOGITS

ponsible

0.17

alog

0.15

adiens

0.15

ERÄ°

0.14

:&

0.14

anou

0.14

/tags

0.14

Ø§ÙģØªÙĩ

0.14

esian

0.14

IRST

0.14

Activations Density 0.016%

mentions of tags and categories within the text

No Comments

No Known Activations