INDEX

Explanations

HTML or XML escape characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

oppable

-0.17

exus

-0.16

putc

-0.15

ogo

-0.14

tin

-0.14

iler

-0.13

ìĦ¤

-0.13

empo

-0.13

ith

-0.13

ÑĩÐµÐ¼

-0.13

POSITIVE LOGITS

sem

0.21

semi

0.19

 semi

0.18

 Semi

0.17

quo

0.15

sem

0.15

quot

0.15

ager

0.15

SEM

0.14

 quot

0.14

Activations Density 0.015%

HTML or XML escape characters

No Comments

No Known Activations