INDEX

Explanations

references to entertainment and content descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 mappings

-0.14

à¸

-0.14

 Fell

-0.14

bia

-0.14

Ìģc

-0.14

amp

-0.13

summ

-0.13

rates

-0.13

 conform

-0.12

æħİ

-0.12

POSITIVE LOGITS

DMIN

0.15

 Leonard

0.15

omain

0.15

åºľ

0.15

Ð¾Ð²Ð¾ÑĢ

0.15

assen

0.14

leared

0.14

ParameterValue

0.14

 Grimm

0.14

hawk

0.13

Activations Density 1.435%

references to entertainment and content descriptions

No Comments

No Known Activations