INDEX

Explanations

specific numerical values or identifiers related to measurements and classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 bloom

-0.15

ServerError

-0.15

ãĥĸãĥŃ

-0.15

eton

-0.15

 harmon

-0.15

 Rich

-0.15

ubi

-0.15

 hind

-0.14

illac

-0.14

Ð³Ð¾

-0.14

POSITIVE LOGITS

çŃĨ

0.16

wall

0.15

erin

0.15

eldon

0.15

uzz

0.14

imon

0.14

aley

0.14

elly

0.14

uzzi

0.14

 Wallace

0.14

Activations Density 0.004%

specific numerical values or identifiers related to measurements and classifications

No Comments

No Known Activations