INDEX

Explanations

references to varied discussion topics within community forums

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

alus

-0.16

äº

-0.15

áº§m

-0.15

 thread

-0.15

à¸·à¹ī

-0.15

emoc

-0.15

astos

-0.15

lex

-0.14

Ø§ÙĪÙĨ

-0.14

_Thread

-0.14

POSITIVE LOGITS

auth

0.16

Occurred

0.15

dued

0.15

variants

0.14

 pits

0.14

inka

0.14

sel

0.14

Activations Density 0.009%

references to varied discussion topics within community forums

No Comments

No Known Activations