INDEX

Explanations

references to the audience or user directly

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

urette

-0.17

-0.16

assoc

-0.14

abbo

-0.14

rescia

-0.14

âĢĮØ³ÛĮ

-0.14

asal

-0.14

 Gate

-0.14

usercontent

-0.13

modele

-0.13

POSITIVE LOGITS

elo

0.15

arkin

0.15

iat

0.15

bol

0.14

core

0.14

ent

0.14

ç¿¼

0.14

ialized

0.14

csr

0.14

entifier

0.14

Activations Density 0.085%

references to the audience or user directly

No Comments

No Known Activations