INDEX

Explanations

names and identifiers associated with people, places, and specific entities in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

arger

-0.18

 derby

-0.15

pus

-0.15

eo

-0.15

enton

-0.15

erland

-0.15

iler

-0.14

eneg

-0.14

enter

-0.14

Century

-0.14

POSITIVE LOGITS

orque

0.15

@qq

0.15

 Extr

0.14

Mappings

0.14

 extr

0.14

 overt

0.14

Ļæ±Ł

0.14

egral

0.14

verse

0.14

Activations Density 0.071%

names and identifiers associated with people, places, and specific entities in a document

No Comments

No Known Activations