INDEX

Explanations

terms related to entertainment, specifically focusing on media formats and their attributes

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

è¾ĳ

-0.15

 termin

-0.15

eldorf

-0.14

etler

-0.14

iyel

-0.14

ARSER

-0.14

Ã¡Å¡

-0.14

ÄĽr

-0.14

Sampler

-0.14

Ã©v

-0.14

POSITIVE LOGITS

ike

0.15

æĺŃ

0.15

ah

0.15

ool

0.14

rah

0.14

Van

0.14

oty

0.14

naw

0.14

lic

0.14

ery

0.14

Activations Density 0.004%

terms related to entertainment, specifically focusing on media formats and their attributes

No Comments

No Known Activations