INDEX

Explanations

specific procedural actions or instructions often related to scheduling or system commands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

.bunifuFlatButton

-0.14

inou

-0.14

 Benton

-0.14

cairo

-0.14

wner

-0.13

 DropIndex

-0.13

 Continued

-0.13

BR

-0.13

 Germ

-0.13

 Owners

-0.13

POSITIVE LOGITS

etto

0.15

enstein

0.15

ÑĪÐ¸Ð±ÐºÐ°

0.14

emy

0.14

pekt

0.14

igious

0.14

lish

0.14

htub

0.14

urtle

0.14

 Crack

0.14

Activations Density 0.722%

specific procedural actions or instructions often related to scheduling or system commands

No Comments

No Known Activations