INDEX

Explanations

terms related to achievements or recognition in a person's life

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

 Bast

-0.16

gin

-0.15

ndo

-0.15

anske

-0.14

PD

-0.14

koc

-0.14

 Harness

-0.14

ific

-0.14

omial

-0.14

insky

-0.14

POSITIVE LOGITS

elt

0.21

enen

0.18

lt

0.18

sehen

0.17

odos

0.15

GenerationStrategy

0.15

.ActionListener

0.15

enever

0.15

ener

0.15

TabPage

0.15

Activations Density 0.007%

terms related to achievements or recognition in a person's life

No Comments

No Known Activations