INDEX

Explanations

Boolean values indicating truthiness or falsiness in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

/latest

-0.17

hesive

-0.15

MLElement

-0.15

OrDefault

-0.15

/meta

-0.15

mitters

-0.15

ools

-0.14

ngÃ¶r

-0.14

 subtype

-0.14

iores

-0.14

POSITIVE LOGITS

atus

0.15

ergy

0.15

 Dress

0.14

pq

0.14

wal

0.14

emas

0.14

pong

0.14

 prospects

0.14

aul

0.14

ilde

0.14

Activations Density 0.030%

Boolean values indicating truthiness or falsiness in code

No Comments

No Known Activations

Boolean values indicating truthiness or falsiness in code

No Comments

No Known Activations