INDEX

Explanations

pronouns indicating personal or collective identities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

tro

-0.15

HasBeen

-0.14

("

-0.14

 ford

-0.14

empor

-0.14

Was

-0.13

ariate

-0.13

osg

-0.13

rette

-0.13

ãĥ£

-0.13

POSITIVE LOGITS

pher

0.16

/she

0.15

kea

0.15

ela

0.14

ê³¤

0.14

’d

0.14

ieurs

0.13

/we

0.13

iner

0.13

enie

0.13

Activations Density 0.163%

pronouns indicating personal or collective identities

No Comments

No Known Activations