INDEX

Explanations

references to evidence or ideas of betrayal and underlying motives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ollo

-0.17

æľĢè¿ĳ

-0.15

cly

-0.15

abler

-0.14

ehr

-0.14

 relief

-0.14

.Assembly

-0.14

ietf

-0.13

.deb

-0.13

 newcom

-0.13

POSITIVE LOGITS

nex

0.17

nor

0.16

nor

0.16

Nor

0.15

 hence

0.15

And

0.15

enor

0.15

observe

0.15

 Gregory

0.15

 OTHERWISE

0.15

Activations Density 0.031%

references to evidence or ideas of betrayal and underlying motives

No Comments

No Known Activations