INDEX

Explanations

specific references to locations or institutions connected to healthcare, political figures, or transportation systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

raud

-0.17

 Sevilla

-0.15

 Webster

-0.15

ihu

-0.15

ething

-0.15

Gir

-0.15

berger

-0.15

pository

-0.15

antha

-0.14

linger

-0.14

POSITIVE LOGITS

è½¯

0.15

avra

0.14

-stats

0.14

alus

0.14

µ

0.14

WC

0.14

 herpes

0.14

eds

0.13

ri

0.13

InMillis

0.13

Activations Density 0.749%

specific references to locations or institutions connected to healthcare, political figures, or transportation systems

No Comments

No Known Activations