INDEX

Explanations

specific articles and indicators of categories, moments, or events in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

iki

-0.14

à¸£à¸°

-0.14

ÑĨÐµÐ¼

-0.14

imo

-0.14

reads

-0.13

outs

-0.13

çĲĨçĶ±

-0.13

atas

-0.13

hte

-0.13

upon

-0.13

POSITIVE LOGITS

bid

0.29

 effort

0.28

 nutshell

0.26

 interview

0.25

 move

0.25

 twist

0.24

 sense

0.21

Bid

0.20

 recent

0.20

 attempt

0.20

Activations Density 0.051%

specific articles and indicators of categories, moments, or events in a narrative context

No Comments

No Known Activations