INDEX

Explanations

terms related to specific food types or substances, particularly in culinary or dietary contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

owell

-0.15

aille

-0.15

Checkpoint

-0.14

ÏĥÎ¿

-0.14

aÅ¼

-0.14

cott

-0.14

ardin

-0.13

è¿·

-0.13

reds

-0.13

anken

-0.13

POSITIVE LOGITS

LOPT

0.17

otope

0.16

iam

0.15

 prospects

0.15

 scopes

0.15

opsis

0.14

çµ¡

0.14

tember

0.14

Mas

0.14

 Donne

0.14

Activations Density 0.254%

terms related to specific food types or substances, particularly in culinary or dietary contexts

No Comments

No Known Activations