INDEX

Explanations

references to entertainment

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

Ð»Ð°Ð´Ð¸

-0.14

 (č↵

-0.14

ucer

-0.14

-generic

-0.14

HONE

-0.14

ÙĦÛĮÙĦ

-0.13

 Alman

-0.13

íķĻìĥĿ

-0.13

 AssemblyVersion

-0.13

_mC

-0.13

POSITIVE LOGITS

amba

0.15

istrov

0.15

cts

0.14

 Prelude

0.14

stown

0.14

Cra

0.14

eldon

0.14

0.13

hotmail

0.13

lenmesi

0.13

Activations Density 0.000%

references to entertainment

No Comments

No Known Activations