INDEX

Explanations

phrases indicating initial actions or steps toward achieving solutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 Guid

-0.15

orman

-0.15

usercontent

-0.14

 fate

-0.14

anten

-0.14

uben

-0.13

alles

-0.13

aman

-0.13

STANCE

-0.13

POSITIVE LOGITS

 starters

0.21

 step

0.20

 begin

0.20

 Partial

0.19

 start

0.19

 partial

0.18

 begins

0.18

Towards

0.17

 progress

0.17

 Begin

0.17

Activations Density 0.192%

phrases indicating initial actions or steps toward achieving solutions

No Comments

No Known Activations