INDEX

Explanations

specific quantities and references to counting or measuring items

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

isku

-0.18

iol

-0.17

//{{

-0.16

Ãªu

-0.15

ergy

-0.15

okit

-0.15

oger

-0.15

igon

-0.15

conde

-0.15

SingleNode

-0.14

POSITIVE LOGITS

 Edition

0.14

asted

0.14

 McGu

0.14

kin

0.14

quist

0.14

els

0.14

avery

0.13

Î³Î·

0.13

assen

0.13

olor

0.13

Activations Density 0.023%

specific quantities and references to counting or measuring items

No Comments

No Known Activations