INDEX

Explanations

occurrences of the word "in" and its context within various phrases or descriptions

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

mant

-0.15

oro

-0.15

uts

-0.14

 courte

-0.14

 Sense

-0.14

 sense

-0.14

iz

-0.14

anto

-0.13

POSITIVE LOGITS

ownik

0.22

 front

0.20

 FRONT

0.18

ieres

0.17

 Formation

0.17

 frente

0.17

 silence

0.17

 formation

0.16

 harms

0.16

 silhouette

0.16

Activations Density 0.183%

occurrences of the word "in" and its context within various phrases or descriptions

No Comments

No Known Activations