INDEX

Explanations

details about events with significant implications or legal consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

rani

-0.15

 Fucking

-0.15

lar

-0.15

nau

-0.15

arken

-0.15

angi

-0.14

íĻĢ

-0.14

egal

-0.14

 ìłĦìļ©

-0.14

ipsis

-0.14

POSITIVE LOGITS

dbl

0.16

 starting

0.15

 Urban

0.14

lik

0.14

 departing

0.14

worth

0.14

 what

0.14

Lik

0.13

dbl

0.13

.constant

0.13

Activations Density 0.003%

details about events with significant implications or legal consequences

No Comments

No Known Activations