INDEX

Explanations

references to candidates or selections in various contexts, particularly in competitive situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

-0.17

-0.15

arin

-0.15

ROUT

-0.14

»¿

-0.14

 hourly

-0.14

ÑħÐ¾Ð´Ð¸Ð¼

-0.14

ĵį

-0.13

POSITIVE LOGITS

ashes

0.15

ovna

0.15

0.14

ynos

0.14

enie

0.14

ulan

0.14

inker

0.14

brook

0.14

elman

0.13

 Beard

0.13

Activations Density 0.000%

references to candidates or selections in various contexts, particularly in competitive situations

No Comments

No Known Activations