INDEX

Explanations

references to public spaces or actions that take place in public

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

otte

-0.18

 Casc

-0.16

ROL

-0.15

inka

-0.15

rol

-0.14

cia

-0.14

.roll

-0.14

seau

-0.14

otti

-0.13

_detach

-0.13

POSITIVE LOGITS

ker

0.19

kelig

0.17

 HÃ¼s

0.16

KER

0.16

 career

0.15

 Career

0.15

áº¿u

0.14

rvÃ©

0.14

pace

0.14

æĬŀ

0.14

Activations Density 0.157%

references to public spaces or actions that take place in public

No Comments

No Known Activations