INDEX

Explanations

references to aspects of behavior and decision-making

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

udu

-0.17

æ½®

-0.15

akens

-0.14

ÑĢÑı

-0.14

uro

-0.14

 Furn

-0.14

 getSource

-0.13

ok

-0.13

 furn

-0.13

ne

-0.13

POSITIVE LOGITS

0.15

 migrationBuilder

0.15

subcategory

0.15

astr

0.14

ContentLoaded

0.14

_NOW

0.14

ð

0.14

ivec

0.14

ResultsController

0.14

Activations Density 0.492%

references to aspects of behavior and decision-making

No Comments

No Known Activations