INDEX

Explanations

discussions about legal definitions and distinctions related to sexual offenses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

oric

-0.16

 rouge

-0.15

oft

-0.14

 respective

-0.14

ãģ«ãģ¦

-0.14

akit

-0.13

 somew

-0.13

igest

-0.13

åĨµ

-0.13

ulong

-0.13

POSITIVE LOGITS

 kinds

0.18

 pylint

0.16

ami

0.16

ÂĨ

0.15

 embar

0.15

("

0.14

Ĩ

0.14

ongo

0.14

 FIXME

0.14

Activations Density 3.953%

discussions about legal definitions and distinctions related to sexual offenses

No Comments

No Known Activations