INDEX

Explanations

content ratings and classifications in media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

dorf

-0.16

ARK

-0.16

arkan

-0.16

èĨľ

-0.15

isse

-0.15

pit

-0.14

ari

-0.13

èĳ

-0.13

cci

-0.13

antt

-0.13

POSITIVE LOGITS

 rated

0.45

 rating

0.44

PG

0.44

 Rated

0.41

 Rating

0.40

Rating

0.40

-rated

0.40

 ratings

0.38

PG

0.38

rating

0.37

Activations Density 0.053%

content ratings and classifications in media

No Comments

No Known Activations