INDEX

Explanations

indications of time duration or quantity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

td

-0.18

argent

-0.17

TD

-0.15

aman

-0.15

Comple

-0.14

uv

-0.14

weed

-0.14

 Comple

-0.14

occ

-0.14

POSITIVE LOGITS

 worth

0.24

 Worth

0.19

worth

0.18

quo

0.16

UTTON

0.16

 spent

0.15

sworth

0.15

ender

0.15

shint

0.14

createQuery

0.14

Activations Density 0.089%

indications of time duration or quantity

No Comments

No Known Activations