INDEX

Explanations

names of athletes, teams, and associated statistics or performance metrics

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

aÃ§

-0.16

alach

-0.15

Atom

-0.15

aÄĩ

-0.15

 Kurul

-0.14

aroo

-0.14

jab

-0.14

 Riot

-0.14

atoire

-0.14

atform

-0.13

POSITIVE LOGITS

 also

0.17

apol

0.15

å°ļ

0.15

bid

0.15

Bid

0.15

ÏĥÎ±Î½

0.15

 meanwhile

0.14

bare

0.14

 count

0.14

 nearby

0.14

Activations Density 0.046%

names of athletes, teams, and associated statistics or performance metrics

No Comments

No Known Activations