INDEX

Explanations

terms related to winning and victory

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

rawer

-0.16

Ð°Ð½Ð¾Ð²

-0.15

anst

-0.14

illos

-0.14

anela

-0.14

ellen

-0.14

ilenames

-0.14

æ³

-0.14

 Prem

-0.14

#__

-0.14

POSITIVE LOGITS

Ð½ÑĥÑĤ

0.21

nut

0.20

Ð»Ð°

0.18

uci

0.18

nu

0.18

nu

0.18

cia

0.17

nut

0.17

Ð½ÑĥÑĤÐ¸

0.17

ikk

0.17

Activations Density 0.030%

terms related to winning and victory

No Comments

No Known Activations