INDEX

Explanations

references to libraries and archives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

irsch

-0.14

á»©

-0.14

ensch

-0.14

ãĥĹãĥª

-0.14

 ÙħØ¹ÙĦÙĪÙħØ§Øª

-0.14

stal

-0.13

kÃ¶

-0.13

Alive

-0.13

etas

-0.13

chein

-0.13

POSITIVE LOGITS

agini

0.15

ëĬ¥

0.15

tip

0.14

Ã³Å¼

0.14

cles

0.14

OURCE

0.14

 PartialView

0.14

 tipped

0.14

 tips

0.14

zcze

0.14

Activations Density 0.037%

references to libraries and archives

No Comments

No Known Activations