INDEX

Explanations

specific programming or coding terminology

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

agal

-0.19

elight

-0.16

LER

-0.15

à¸¹à¹Ħ

-0.14

 Glover

-0.14

ahun

-0.14

inte

-0.14

aceae

-0.14

ramework

-0.14

POSITIVE LOGITS

ional

0.14

CHASE

0.14

rawl

0.14

Î¬ÏĤ

0.13

 cent

0.13

 Representative

0.13

kem

0.13

Millis

0.13

ibo

0.13

Gap

0.13

Activations Density 0.255%

specific programming or coding terminology

No Comments

No Known Activations

specific programming or coding terminology

No Comments

No Known Activations