INDEX

Explanations

quantitative performance statistics related to sports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

FromClass

-0.17

erval

-0.14

outine

-0.14

Wr

-0.14

ahy

-0.14

lore

-0.14

umba

-0.13

 unsafe

-0.13

aid

-0.13

POSITIVE LOGITS

Dating

0.18

 Dating

0.17

 dating

0.17

 overall

0.17

lifetime

0.15

overall

0.15

dating

0.15

Ŀ

0.15

 inclus

0.15

including

0.14

Activations Density 0.043%

quantitative performance statistics related to sports

No Comments

No Known Activations