INDEX

Explanations

references to New York City

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

atform

-0.18

ÑĢÐ¾ÑĪ

-0.16

adients

-0.16

Ã¡bado

-0.15

_subscribe

-0.15

itag

-0.14

ertino

-0.14

anova

-0.14

Äįek

-0.14

isplay

-0.14

POSITIVE LOGITS

 Polic

0.16

 Bernstein

0.14

uto

0.14

anky

0.14

ISA

0.14

fal

0.14

ãĥ¼ãĥĢ

0.14

AP

0.14

 Actual

0.13

 Scri

0.13

Activations Density 0.001%

references to New York City

No Comments

No Known Activations