INDEX

Explanations

text related to entertainment topics

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

arius

-0.18

uv

-0.15

UTH

-0.15

ÅĦst

-0.14

ayah

-0.14

occ

-0.14

antic

-0.14

 Treasury

-0.14

erc

-0.14

ohn

-0.14

POSITIVE LOGITS

lor

0.16

TOT

0.14

emean

0.14

ammad

0.14

ifter

0.14

hazi

0.14

esson

0.14

anco

0.13

 Ã©lect

0.13

æĹ

0.13

Activations Density 0.000%

text related to entertainment topics

No Comments

No Known Activations