INDEX

Explanations

terms related to sports winning and losing streaks

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

ÏģÏī

-0.16

ione

-0.15

alla

-0.15

chos

-0.14

linger

-0.14

lion

-0.13

FXML

-0.13

discover

-0.13

iers

-0.13

Split

-0.13

POSITIVE LOGITS

 streak

0.54

run

0.33

 string

0.31

 stretch

0.27

 longest

0.25

 winning

0.25

 spell

0.25

 strings

0.22

run

0.22

(string

0.22

Activations Density 0.077%

terms related to sports winning and losing streaks

No Comments

No Known Activations