INDEX

Explanations

references to time periods, specifically years and seasons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

Ð¾Ð·Ð°

-0.15

ubern

-0.15

peater

-0.14

itele

-0.14

oya

-0.14

elter

-0.14

angelog

-0.14

sak

-0.14

æĿī

-0.14

-0.13

POSITIVE LOGITS

RS

0.15

SR

0.14

ertz

0.14

ify

0.14

oper

0.14

TS

0.13

lint

0.13

ition

0.13

PubMed

0.13

Pro

0.13

Activations Density 0.004%

references to time periods, specifically years and seasons

No Comments

No Known Activations