INDEX

Explanations

terms related to missing persons and their cases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

trag

-0.15

gers

-0.14

rat

-0.14

ãĤĵãģ¨

-0.14

plen

-0.14

fried

-0.14

adora

-0.13

ÏĤ

-0.13

IGNAL

-0.13

POSITIVE LOGITS

chal

0.16

cie

0.16

enze

0.15

dal

0.15

 emploi

0.15

 teeth

0.14

entre

0.14

elter

0.14

 missing

0.14

aires

0.14

Activations Density 0.007%

terms related to missing persons and their cases

No Comments

No Known Activations