INDEX

Explanations

expressions of opinions and evaluations regarding sports teams and their performance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

_REF

-0.15

wart

-0.14

structors

-0.13

inson

-0.13

elpers

-0.13

PTS

-0.13

/*č↵

-0.13

 surprisingly

-0.13

irms

-0.13

urette

-0.13

POSITIVE LOGITS

 whole

0.18

 thing

0.17

DNA

0.15

 entire

0.15

alach

0.15

 other

0.15

äºĭæĥħ

0.14

ammer

0.14

dna

0.14

otypical

0.13

Activations Density 0.294%

expressions of opinions and evaluations regarding sports teams and their performance

No Comments

No Known Activations