INDEX

Explanations

technical terms related to contributions and modifications in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

Mods

-0.14

cci

-0.14

Ley

-0.14

stinian

-0.14

umbo

-0.14

duk

-0.14

atab

-0.14

mods

-0.14

 Ernest

-0.13

æ®¿

-0.13

POSITIVE LOGITS

azzi

0.16

ãĥķãĤ

0.14

ìĬ¹

0.14

ãģĵ

0.14

jud

0.14

ardi

0.14

nu

0.14

.Toolkit

0.14

ieten

0.14

_priv

0.14

Activations Density 0.347%

technical terms related to contributions and modifications in scientific contexts

No Comments

No Known Activations