INDEX

Explanations

references to current activities or statuses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

beck

-0.15

ayer

-0.14

Fle

-0.14

 Sanctuary

-0.14

iva

-0.14

bove

-0.14

 Schneider

-0.14

tm

-0.14

ta

-0.14

POSITIVE LOGITS

roman

0.18

chu

0.16

gorm

0.16

AsyncResult

0.15

orida

0.15

ìķ½

0.15

 Ingram

0.15

atura

0.14

CPL

0.14

assed

0.14

Activations Density 0.077%

references to current activities or statuses

No Comments

No Known Activations