INDEX

Explanations

references to specific years

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

elf

-0.17

elic

-0.17

/GPL

-0.16

weed

-0.14

oline

-0.14

-cur

-0.14

spo

-0.14

ero

-0.14

uto

-0.14

ector

-0.14

POSITIVE LOGITS

-round

0.17

ä»½

0.17

-olds

0.15

stown

0.15

-old

0.15

sville

0.14

nder

0.14

nty

0.14

rak

0.14

Activations Density 0.084%

references to specific years

No Comments

No Known Activations