INDEX

Explanations

actions associated with decision-making and participation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

orer

-0.17

iable

-0.15

chw

-0.15

éĢ

-0.15

noop

-0.14

odont

-0.14

 migrationBuilder

-0.14

-dismissible

-0.14

UST

-0.14

reachable

-0.14

POSITIVE LOGITS

 future

0.17

external

0.16

 higher

0.16

 apprentices

0.16

 external

0.15

future

0.15

ati

0.15

 Apprent

0.15

ropoda

0.14

 succession

0.14

Activations Density 0.028%

actions associated with decision-making and participation

No Comments

No Known Activations