INDEX

Explanations

phrases indicating complexity or difficulty in tasks or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ahl

-0.17

á»¹

-0.16

fad

-0.15

done

-0.15

 Conduct

-0.15

 Doing

-0.15

raj

-0.14

 conducted

-0.14

Æ¡i

-0.14

isque

-0.14

POSITIVE LOGITS

æĭ¥

0.15

minate

0.15

andles

0.15

olo

0.14

enos

0.14

ictionaries

0.14

 Strom

0.14

_repr

0.14

gh

0.13

sink

0.13

Activations Density 0.221%

phrases indicating complexity or difficulty in tasks or situations

No Comments

No Known Activations