INDEX

Explanations

numerical or coded references that indicate a specific organizational structure or listing

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

Ú©Ø´

-0.16

à¤¦à¤®

-0.16

rezent

-0.14

.openConnection

-0.14

_logic

-0.14

 Binder

-0.14

regn

-0.13

 pant

-0.13

Iss

-0.13

adan

-0.13

POSITIVE LOGITS

gos

0.15

 Throw

0.15

sher

0.15

ship

0.15

Ear

0.14

ï»¿↵↵

0.14

Ear

0.14

 cord

0.14

cord

0.14

Activations Density 0.002%

numerical or coded references that indicate a specific organizational structure or listing

No Comments

No Known Activations