INDEX

Explanations

phrases related to compliance and non-compliance in a legal or authoritarian context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

Taj

-0.15

uars

-0.15

 è±

-0.14

³

-0.14

abox

-0.14

inin

-0.14

phinx

-0.14

éľĩ

-0.14

iaux

-0.13

POSITIVE LOGITS

Î½Î±Î½

0.15

INDOW

0.15

ETY

0.14

brook

0.14

brtc

0.14

otel

0.14

 Rubin

0.14

Ø±Ùģ

0.14

BCH

0.14

Ped

0.14

Activations Density 0.027%

phrases related to compliance and non-compliance in a legal or authoritarian context

No Comments

No Known Activations