INDEX

Explanations

words related to various forms of entertainment or media representation

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

Ð·Ñĭ

-0.14

GenerationStrategy

-0.14

avar

-0.14

urai

-0.14

ekl

-0.13

oro

-0.13

Ã¹i

-0.13

uku

-0.13

\Active

-0.13

HING

-0.13

POSITIVE LOGITS

ots

0.15

ote

0.15

otate

0.14

 another

0.14

 world

0.13

abd

0.13

hed

0.13

bla

0.13

 bonds

0.13

bol

0.13

Activations Density 0.022%

words related to various forms of entertainment or media representation

No Comments

No Known Activations

words related to various forms of entertainment or media representation

No Comments

No Known Activations