INDEX

Explanations

references to specific pieces of advice or guidelines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

fet

-0.17

ura

-0.17

TEGER

-0.14

uctive

-0.14

irit

-0.13

ä¸Ģç§į

-0.13

çĦ

-0.13

ÑĢÑĥÑĤ

-0.13

oteric

-0.13

POSITIVE LOGITS

 equipment

0.18

 legislation

0.18

 advice

0.18

PIE

0.17

 piece

0.16

 pieces

0.16

 evidence

0.16

acre

0.16

islation

0.16

 info

0.15

Activations Density 0.031%

references to specific pieces of advice or guidelines

No Comments

No Known Activations