INDEX

Explanations

references to organizations and committees

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

lesi

-0.19

nell

-0.18

');?></

-0.15

idge

-0.14

_DECLARE

-0.14

ummer

-0.14

nat

-0.14

ione

-0.13

te

-0.13

lege

-0.13

POSITIVE LOGITS

uzu

0.16

ans

0.15

vvm

0.14

olec

0.14

apia

0.14

#(

0.14

iration

0.14

ieder

0.13

 Frid

0.13

_ENTRIES

0.13

Activations Density 0.042%

references to organizations and committees

No Comments

No Known Activations