INDEX

Explanations

references to reality television shows and their elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

atown

-0.16

avern

-0.15

ouro

-0.15

rawer

-0.15

Ãºa

-0.15

ivable

-0.15

mares

-0.15

atism

-0.15

Ð¾ÑĢÐ°Ñı

-0.14

 Ð¿Ð¾Ð±Ð°

-0.14

POSITIVE LOGITS

 daily

0.17

 contestants

0.16

asÄ±na

0.16

villa

0.15

 contestant

0.14

Mon

0.14

çĢ¬

0.14

hooks

0.14

Activations Density 0.002%

references to reality television shows and their elements

No Comments

No Known Activations