INDEX

Explanations

instances of the word "dod" or related forms, typically indicating avoidance or evasion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

auen

-0.18

 Garrison

-0.17

 Gauge

-0.15

ophon

-0.15

asser

-0.15

 Sher

-0.14

ullan

-0.14

lessly

-0.14

/bg

-0.14

ÙĥÙĬÙĬÙģ

-0.14

POSITIVE LOGITS

ging

0.53

ges

0.49

ged

0.46

gem

0.38

ger

0.37

gy

0.34

gew

0.34

GING

0.33

gers

0.32

gement

0.30

Activations Density 0.013%

instances of the word "dod" or related forms, typically indicating avoidance or evasion

No Comments

No Known Activations