INDEX

Explanations

occurrences of names and specific references to notable figures or settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

aghan

-0.17

pea

-0.15

ìĺģìĥģ

-0.15

alsex

-0.14

mscorlib

-0.14

VersionUID

-0.14

ijing

-0.14

 Ð¿Ð¾Ð±Ð°

-0.13

Bes

-0.13

edula

-0.13

POSITIVE LOGITS

elle

0.15

dro

0.14

hin

0.14

Dro

0.14

foot

0.14

utto

0.14

Î¼Î¼Î±

0.14

ruc

0.14

utta

0.14

ipp

0.14

Activations Density 0.222%

occurrences of names and specific references to notable figures or settings

No Comments

No Known Activations