INDEX

Explanations

specific entities and terms related to data and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

Ä±kl

-0.15

ekk

-0.15

rer

-0.14

 TLabel

-0.14

ãĥĲãĥ¼

-0.14

iese

-0.14

 Johnston

-0.14

à¸£à¸£à¸Ħ

-0.14

à¸£à¸£

-0.14

ButtonText

-0.13

POSITIVE LOGITS

 Mattis

0.16

0.14

 irres

0.14

sos

0.13

 Ritch

0.13

 Ãºn

0.13

 Rash

0.13

CTL

0.13

Activations Density 0.021%

specific entities and terms related to data and statistics

No Comments

No Known Activations

specific entities and terms related to data and statistics

No Comments

No Known Activations