INDEX

Explanations

unique identifiers or names, particularly related to locations or entities

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

erner

-0.17

gu

-0.16

linger

-0.16

ainter

-0.16

otal

-0.16

inde

-0.15

edl

-0.15

pow

-0.15

ãģĬãĤĬ

-0.14

 Oriental

-0.14

POSITIVE LOGITS

ÏĮ

0.15

idd

0.15

clerosis

0.15

ÑĪÑĤ

0.15

Bak

0.14

recht

0.13

 McCabe

0.13

Ø§ÙĬØ§

0.13

Ð°ÑĤÐ¾

0.13

Activations Density 0.020%

unique identifiers or names, particularly related to locations or entities

No Comments

No Known Activations