INDEX

Explanations

terms related to places, states, or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

Ð½Ð°Ð´Ð»ÐµÐ¶

-0.15

 Scratch

-0.15

undry

-0.15

aliz

-0.14

nees

-0.14

 equalTo

-0.13

(strict

-0.13

kyt

-0.13

ammers

-0.13

POSITIVE LOGITS

oka

0.15

aki

0.14

anga

0.14

 Rahman

0.14

ault

0.14

ouch

0.13

Mailer

0.13

 Rubin

0.13

 prefect

0.13

Activations Density 0.010%

terms related to places, states, or conditions

No Comments

No Known Activations