INDEX

Explanations

concepts related to foundational elements or groundwork for ideas, projects, or discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

iga

-0.16

ouve

-0.15

argent

-0.15

ond

-0.15

omain

-0.15

 front

-0.14

ongan

-0.14

åķĬåķĬ

-0.14

iqu

-0.14

mong

-0.14

POSITIVE LOGITS

/base

0.16

for

0.15

yro

0.15

 Humph

0.14

hazi

0.14

_drawer

0.14

Ãºt

0.14

Activations Density 0.061%

concepts related to foundational elements or groundwork for ideas, projects, or discussions

No Comments

No Known Activations