INDEX

Explanations

expressions of uncertainty or questioning thought processes

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

swer

-0.15

oth

-0.15

Carthy

-0.14

eÃ§

-0.14

 mask

-0.14

ugin

-0.14

inn

-0.13

 Mask

-0.13

ery

-0.13

unw

-0.13

POSITIVE LOGITS

-regexp

0.16

_Cmd

0.15

gang

0.14

asmus

0.14

 tipped

0.14

dere

0.14

xfb

0.14

ÑĩÐºÐ¸

0.14

Ã¡r

0.14

ÐĲÑĢÑħÑĸÐ²

0.14

Activations Density 0.000%

expressions of uncertainty or questioning thought processes

No Comments

No Known Activations