INDEX

Explanations

phrases or contexts relating to a sense of occurrence or presence

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

baugh

-0.16

atter

-0.15

reur

-0.15

ubo

-0.14

&t

-0.14

icom

-0.14

ãĤĩ

-0.14

stan

-0.14

POSITIVE LOGITS

ÑıÑģ

0.14

entai

0.14

 links

0.14

enville

0.14

/details

0.14

 Provid

0.14

 Ivanka

0.14

loit

0.13

pong

0.13

liÄŁinde

0.13

Activations Density 0.003%

phrases or contexts relating to a sense of occurrence or presence

No Comments

No Known Activations