INDEX

Explanations

configuration and system settings related to server and user properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

=function

-0.15

 purge

-0.15

legg

-0.14

bidden

-0.14

/../

-0.14

andy

-0.14

Ãªn

-0.14

ÐĴÐĲ

-0.13

.AddDays

-0.13

abis

-0.13

POSITIVE LOGITS

ifact

0.17

_TILE

0.15

chÃ©

0.14

iro

0.14

orElse

0.13

åĽł

0.13

 cheek

0.13

anje

0.13

ãĤ¦ãĥĪ

0.12

_preference

0.12

Activations Density 0.291%

configuration and system settings related to server and user properties

No Comments

No Known Activations