INDEX

Explanations

statements or claims made by individuals

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 perfected

-0.15

ifu

-0.15

cus

-0.14

beg

-0.14

 Fiscal

-0.14

tog

-0.14

ìļ±

-0.14

æĺŃåĴĮ

-0.13

atron

-0.13

ella

-0.13

POSITIVE LOGITS

lice

0.15

stroy

0.15

ļĮ

0.15

bove

0.15

uste

0.14

XB

0.14

dap

0.14

resa

0.14

sea

0.14

Activations Density 0.764%

statements or claims made by individuals

No Comments

No Known Activations