INDEX

Explanations

references to entities or specific points of interest within different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 Gilles

-0.17

ears

-0.15

gage

-0.15

igua

-0.14

çĶ

-0.14

udder

-0.14

asin

-0.14

CDC

-0.14

oire

-0.14

elden

-0.14

POSITIVE LOGITS

 Hass

0.15

ynthia

0.15

ateway

0.15

olec

0.14

resh

0.14

anked

0.14

Asp

0.14

æĺĮ

0.14

 Shah

0.14

Activations Density 0.010%

references to entities or specific points of interest within different contexts

No Comments

No Known Activations