INDEX

Explanations

numerical values in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

à¸´à¸ģà¸²

-0.14

ÅĤa

-0.14

 Libert

-0.14

 Guerrero

-0.13

lez

-0.13

iÄĩ

-0.13

Äįe

-0.13

 CURLOPT

-0.13

vig

-0.13

 âĢª

-0.13

POSITIVE LOGITS

ë²ĦìłĦ

0.15

/latest

0.15

0.14

Ñħ

0.14

older

0.14

OLDER

0.14

latest

0.14

 harassing

0.14

Bounding

0.14

rpc

0.14

Activations Density 0.024%

numerical values in a technical context

No Comments

No Known Activations