INDEX

Explanations

data-related terms and metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

-0.16

pons

-0.15

adows

-0.14

ÙĪØ§Ø²

-0.14

opp

-0.14

sav

-0.14

ter

-0.14

abeth

-0.14

/i

-0.14

POSITIVE LOGITS

usercontent

0.19

\uc

0.18

InParameter

0.16

ForRow

0.16

uParam

0.16

styleType

0.15

 addCriterion

0.15

isContained

0.15

ocrates

0.15

mtree

0.14

Activations Density 0.034%

data-related terms and metrics

No Comments

No Known Activations