INDEX

Explanations

quoted strings, especially with specific formatting or attributes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

rysler

-0.16

cient

-0.14

ANNEL

-0.14

gnore

-0.14

tha

-0.14

abox

-0.14

.Slf

-0.14

-selection

-0.13

iga

-0.13

 dÃ¢y

-0.13

POSITIVE LOGITS

 Blanch

0.17

 reinst

0.15

ovolta

0.14

ÙĦØŃ

0.13

Tow

0.13

argo

0.13

aser

0.13

lean

0.13

rowsable

0.13

Â¤

0.13

Activations Density 0.072%

quoted strings, especially with specific formatting or attributes

No Comments

No Known Activations