INDEX

Explanations

references to personal experiences or relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 ones

-0.17

wp

-0.16

raz

-0.15

_RECV

-0.15

ENSE

-0.14

 hers

-0.14

ponential

-0.14

arov

-0.14

ultipart

-0.14

cl

-0.14

POSITIVE LOGITS

udget

0.18

done

0.18

ToDo

0.18

steder

0.16

 Done

0.16

 done

0.15

Done

0.15

_done

0.15

/loose

0.14

ê½

0.14

Activations Density 0.239%

references to personal experiences or relationships

No Comments

No Known Activations