INDEX

Explanations

references to numbers and symbols in a formatted or structured context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

anou

-0.16

ady

-0.15

hora

-0.15

ãĥŃãĥ¼

-0.15

CONN

-0.15

idis

-0.15

pad

-0.14

 Replies

-0.14

eper

-0.14

arp

-0.14

POSITIVE LOGITS

Pub

0.18

èĩ¨

0.16

fÃ¼

0.16

eff

0.16

ÑĥÐ½Ð´

0.16

odos

0.16

kola

0.16

 effective

0.16

Pub

0.15

 struck

0.15

Activations Density 0.004%

references to numbers and symbols in a formatted or structured context

No Comments

No Known Activations