INDEX

Explanations

references to San Francisco

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

erras

-0.20

ãĥ¼ãĥ

-0.18

incinn

-0.16

iÃª

-0.16

ekt

-0.15

Ð°ÑĦ

-0.14

stroy

-0.14

Å¯r

-0.14

eyle

-0.14

ierrez

-0.14

POSITIVE LOGITS

ish

0.17

Ìĥ

0.15

obe

0.15

ette

0.15

rtype

0.15

har

0.15

 outlet

0.14

Sab

0.14

Ð»Ð°Ð±

0.14

obot

0.14

Activations Density 0.007%

references to San Francisco

No Comments

No Known Activations