INDEX

Explanations

references to missing or unidentified people and details regarding their historical context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

asley

-0.16

aney

-0.16

agara

-0.16

lik

-0.15

hiro

-0.15

adla

-0.15

 Variables

-0.15

ÐµÐ½ÑĤÐ°

-0.14

eyer

-0.14

åģ

-0.14

POSITIVE LOGITS

.svg

0.15

|int

0.14

çĶ

0.14

/Image

0.14

Ń

0.14

 Pert

0.13

ë¹Ļ

0.13

ged

0.13

Äĩ

0.13

\\/

0.13

Activations Density 0.009%

references to missing or unidentified people and details regarding their historical context

No Comments

No Known Activations