INDEX

Explanations

statements and opinions about beliefs, speculations, and predictions

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

erule

-0.18

aign

-0.16

oler

-0.16

ãģĹãĤĩ

-0.15

spacing

-0.15

esz

-0.15

Łèĥ½

-0.15

uggle

-0.15

elve

-0.14

 Seks

-0.14

POSITIVE LOGITS

InOut

0.15

 simil

0.14

 Consolid

0.14

à¸²à¸§

0.14

rud

0.13

wis

0.13

nam

0.13

ãĥ³ãĥĲ

0.13

 prim

0.13

abb

0.13

Activations Density 0.135%

statements and opinions about beliefs, speculations, and predictions

No Comments

No Known Activations