INDEX

Explanations

specific names and titles related to individuals, organizations, and entities in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ntag

-0.18

apon

-0.16

Ā

-0.15

rint

-0.15

 libertin

-0.14

uml

-0.13

åį«

-0.13

REW

-0.13

edly

-0.13

 Beaut

-0.13

POSITIVE LOGITS

AndGet

0.16

ÑĥÑĢÐ¸

0.15

 Matth

0.14

utto

0.14

 summ

0.14

lein

0.13

 pseud

0.13

 Fury

0.13

turtle

0.13

 lanz

0.13

Activations Density 0.142%

specific names and titles related to individuals, organizations, and entities in various contexts

No Comments

No Known Activations