INDEX

Explanations

quantified measures of distance or time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

akan

-0.17

WISE

-0.15

Kle

-0.15

 Petit

-0.14

Ont

-0.14

ebek

-0.14

atÃŃm

-0.14

iras

-0.14

tbl

-0.13

 nutrit

-0.13

POSITIVE LOGITS

 away

0.77

 Away

0.65

away

0.60

Away

0.56

-away

0.50

 apart

0.35

aways

0.30

weg

0.30

ago

0.25

 Apart

0.24

Activations Density 0.077%

quantified measures of distance or time

No Comments

No Known Activations