INDEX

Explanations

mathematical notation or expressions related to structures and relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

enco

-0.16

emean

-0.15

tics

-0.15

cter

-0.15

zin

-0.15

amed

-0.14

 Morm

-0.14

ETCH

-0.14

orte

-0.14

redd

-0.14

POSITIVE LOGITS

verity

0.14

eyse

0.14

onen

0.14

ContentPane

0.14

vasion

0.14

 Distance

0.14

/key

0.13

\grid

0.13

Activations Density 0.055%

mathematical notation or expressions related to structures and relationships

No Comments

No Known Activations