INDEX

Explanations

references to notable names and numbers, particularly in a specific context

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

apel

-0.15

arc

-0.15

cha

-0.15

thinkable

-0.15

/GPL

-0.14

mailto

-0.14

coc

-0.14

ha

-0.13

ataka

-0.13

ogi

-0.13

POSITIVE LOGITS

enler

0.15

 perm

0.14

oters

0.14

åĭ

0.14

yasal

0.13

/mit

0.13

á¿Ĩ

0.13

URRENT

0.13

taboola

0.13

larak

0.13

Activations Density 0.004%

references to notable names and numbers, particularly in a specific context

No Comments

No Known Activations