INDEX

Explanations

references to villains in various narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

-0.17

KN

-0.16

ifton

-0.14

enberg

-0.14

Peripheral

-0.14

ilis

-0.14

é

-0.14

à¸°

-0.13

Ð¾ÐºÑģÐ¸

-0.13

deme

-0.13

POSITIVE LOGITS

isses

0.16

 tiener

0.15

zym

0.15

odata

0.15

ieÅ¼

0.14

ags

0.14

 Catalyst

0.14

Ã¡r

0.14

alm

0.14

Ð´Ñı

0.14

Activations Density 0.156%

references to villains in various narratives

No Comments

No Known Activations