INDEX

Explanations

instances of actions related to the process of bringing or achieving something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

-0.16

oses

-0.15

iff

-0.14

ANGO

-0.14

 paraph

-0.13

ITCH

-0.13

ward

-0.13

POSITIVE LOGITS

 alive

0.27

alive

0.23

 Alive

0.18

ãĤĵãģ©

0.16

 into

0.16

 Into

0.16

 awake

0.15

ÄĲT

0.14

 Front

0.14

 apart

0.14

Activations Density 0.074%

instances of actions related to the process of bringing or achieving something

No Comments

No Known Activations