INDEX

Explanations

content related to digital media and technology discussions

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

 Holt

-0.16

å»¶

-0.15

 ruku

-0.14

plode

-0.14

 Dere

-0.14

kli

-0.14

ensible

-0.14

 Contemporary

-0.14

tro

-0.14

nez

-0.14

POSITIVE LOGITS

ê

0.15

SCP

0.15

appen

0.15

èĭĹ

0.15

cry

0.15

orget

0.15

inq

0.14

ãĥĥãĥĦ

0.14

eneg

0.14

nod

0.14

Activations Density 0.044%

content related to digital media and technology discussions

No Comments

No Known Activations