INDEX

Explanations

references to death and mortality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

-setting

-0.16

 haired

-0.16

relude

-0.15

izio

-0.15

etta

-0.15

duto

-0.15

edia

-0.14

ERSIST

-0.14

antry

-0.14

dia

-0.14

POSITIVE LOGITS

fully

0.20

bed

0.17

ened

0.16

 pill

0.16

fst

0.15

esda

0.14

 Kendrick

0.14

oppers

0.14

rp

0.14

ilst

0.14

Activations Density 0.043%

references to death and mortality

No Comments

No Known Activations

references to death and mortality

No Comments

No Known Activations