INDEX

Explanations

terms related to structure and organization in writing

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

lash

-0.17

aju

-0.17

 Ø¨Ø§ÙĤ

-0.16

ritic

-0.16

lam

-0.15

rego

-0.15

yar

-0.14

MUX

-0.14

leftright

-0.14

POSITIVE LOGITS

è»

0.17

itori

0.14

athering

0.14

ohon

0.14

ICS

0.14

sequ

0.13

.rev

0.13

ÏĦÏį

0.13

ibble

0.13

olume

0.13

Activations Density 0.001%

terms related to structure and organization in writing

No Comments

No Known Activations