INDEX

Explanations

historical references and notable figures in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 Kata

-0.15

ww

-0.15

uko

-0.14

amen

-0.14

 Evet

-0.14

_notify

-0.14

ÑĤÐµÑĢÐ½

-0.14

Ø§Ø±Ùģ

-0.14

agli

-0.14

anga

-0.13

POSITIVE LOGITS

0.36

0.35

0.34

0.31

 Renaissance

0.29

0.27

0.26

Activations Density 0.083%

historical references and notable figures in a narrative context

No Comments

No Known Activations