INDEX

Explanations

words related to entertainment or media sources

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

pon

-0.15

ypress

-0.15

HONE

-0.15

Rin

-0.15

 Nora

-0.15

kop

-0.15

orney

-0.15

xad

-0.14

itoris

-0.14

kar

-0.14

POSITIVE LOGITS

irst

0.15

Ã¸d

0.15

rite

0.14

aisal

0.14

Ã¶l

0.14

bidden

0.14

istrov

0.14

annie

0.14

 Crosby

0.13

Activations Density 0.000%

words related to entertainment or media sources

No Comments

No Known Activations