INDEX

Explanations

references to gateways and entry points in various contexts

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

 Bryce

-0.17

robe

-0.16

 geil

-0.16

ãĥ¼ãĥ«ãĥī

-0.15

aken

-0.15

kÃ¼

-0.15

ä¿Ĭ

-0.15

outed

-0.14

auty

-0.14

alien

-0.14

POSITIVE LOGITS

htable

0.17

aku

0.15

Sit

0.15

 Hera

0.14

ÑŁ

0.14

å¶

0.14

ows

0.14

 systems

0.14

plotlib

0.14

OT

0.14

Activations Density 0.004%

references to gateways and entry points in various contexts

No Comments

No Known Activations