INDEX

Explanations

references to academic journals and research articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

atures

-0.16

Ð°Ð±Ð¾

-0.14

ouch

-0.14

 homic

-0.14

drag

-0.13

 ones

-0.13

poke

-0.13

ingu

-0.13

gran

-0.13

ê¶Į

-0.13

POSITIVE LOGITS

aira

0.16

formatted

0.15

/frontend

0.15

kw

0.14

KW

0.14

/goto

0.14

mav

0.14

/Dk

0.14

dea

0.13

Activations Density 0.007%

references to academic journals and research articles

No Comments

No Known Activations