INDEX

Explanations

references to female characters or entities in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

-0.18

thon

-0.16

 Tage

-0.16

-0.14

 cult

-0.14

la

-0.14

 giorno

-0.14

-0.13

 coefficient

-0.13

 dolore

-0.13

POSITIVE LOGITS

zos

0.18

 misma

0.17

 academia

0.16

mgr

0.15

 Glover

0.15

Î»ÎµÎº

0.15

quelle

0.15

shal

0.15

enos

0.15

undry

0.15

Activations Density 0.054%

references to female characters or entities in a narrative context

No Comments

No Known Activations