INDEX

Explanations

terms related to attributes or characteristics of various subjects

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ipel

-0.24

rench

-0.17

-0.15

orney

-0.15

 èĦ

-0.15

ë³µ

-0.15

rip

-0.15

Boy

-0.15

dit

-0.15

orna

-0.14

POSITIVE LOGITS

çıł

0.18

 Lambert

0.15

 cÃ´t

0.15

 Fang

0.14

CEED

0.14

 Slee

0.13

æĬĬ

0.13

vos

0.13

aki

0.13

sha

0.13

Activations Density 0.020%

terms related to attributes or characteristics of various subjects

No Comments

No Known Activations