INDEX

Explanations

classifications and age ratings for films and media content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

anko

-0.18

nd

-0.15

 vrou

-0.14

casts

-0.14

 ascend

-0.14

 acquaint

-0.14

 bundles

-0.13

angles

-0.13

 steal

-0.13

POSITIVE LOGITS

 adult

0.18

Fir

0.18

age

0.17

 Mature

0.17

 Adult

0.16

-age

0.15

ubat

0.15

adult

0.15

pgsql

0.15

á»¥n

0.15

Activations Density 0.039%

classifications and age ratings for films and media content

No Comments

No Known Activations