INDEX

Explanations

specific names or terms associated with pasta

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

heimer

-0.17

es

-0.15

ady

-0.14

uire

-0.14

closure

-0.14

 Date

-0.14

çİĩ

-0.14

/forms

-0.13

raid

-0.13

olars

-0.13

POSITIVE LOGITS

0.16

lick

0.15

istani

0.15

iant

0.15

kest

0.15

kir

0.14

 sÃ³c

0.14

 Ð¿ÑĢÐ¾ÑĢ

0.14

ients

0.14

ega

0.14

Activations Density 0.045%

specific names or terms associated with pasta

No Comments

No Known Activations