INDEX

Explanations

terms related to "forensics."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ssp

-0.16

raf

-0.16

rement

-0.16

role

-0.15

ertest

-0.15

rax

-0.15

razil

-0.15

uzzle

-0.15

¼

-0.14

inox

-0.14

POSITIVE LOGITS

nsic

0.45

stry

0.37

casts

0.33

closure

0.31

ns

0.30

most

0.28

caster

0.27

word

0.27

ster

0.26

sters

0.26

Activations Density 0.009%

terms related to "forensics."

No Comments

No Known Activations