INDEX

Explanations

punctuation or symbols that denote special characteristics or functions in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 princ

-0.15

itou

-0.15

 Campos

-0.15

/sn

-0.14

ono

-0.14

Cox

-0.14

 snaps

-0.13

ä¸Ī

-0.13

otal

-0.13

_finalize

-0.13

POSITIVE LOGITS

nable

0.17

Nested

0.15

bens

0.14

ASCADE

0.14

azer

0.14

AsyncResult

0.14

batim

0.14

.rest

0.13

Ð½Ð°Ð´

0.13

cade

0.13

Activations Density 0.047%

punctuation or symbols that denote special characteristics or functions in a text

No Comments

No Known Activations