INDEX

Explanations

references to specific films and critical commentary about them

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ÏĢÎ¹

-0.17

ÑĦÐµÐºÑĤÐ¸Ð²

-0.16

-validate

-0.16

ignon

-0.15

upal

-0.14

 knot

-0.14

ÃĹ↵↵

-0.14

æľĭ

-0.13

 rhet

-0.13

inton

-0.13

POSITIVE LOGITS

0.18

 spoof

0.18

0.14

ousse

0.14

finder

0.14

 Express

0.14

_framework

0.13

iom

0.13

jal

0.13

("`

0.13

Activations Density 0.095%

references to specific films and critical commentary about them

No Comments

No Known Activations