INDEX

Explanations

specific names or terms associated with prominent figures, concepts, or entities related to culture and history

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ogh

-0.15

aten

-0.14

 broad

-0.14

ido

-0.14

ÃŃc

-0.14

wen

-0.14

’n

-0.14

 infl

-0.14

 motion

-0.14

POSITIVE LOGITS

$MESS

0.21

.sourceforge

0.16

sap

0.16

odesk

0.15

ordion

0.14

ArrayOf

0.14

licer

0.14

\grid

0.14

ispecies

0.14

edException

0.14

Activations Density 0.018%

specific names or terms associated with prominent figures, concepts, or entities related to culture and history

No Comments

No Known Activations