INDEX

Explanations

names of notable geographical locations, specifically lakes and plazas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ardi

-0.14

Ð¾Ð»Ð¾Ñģ

-0.14

ENTA

-0.14

GINE

-0.14

ASSES

-0.14

OLER

-0.14

ãĥ³ãĥĹ

-0.14

cki

-0.13

Ð¾Ð¼ÐµÐ½

-0.13

'gc

-0.13

POSITIVE LOGITS

áº¡n

0.15

Re

0.15

oss

0.14

ãĥ¼ãĥł

0.14

 Andres

0.13

ible

0.13

Ch

0.13

éłŃ

0.13

lur

0.13

empo

0.13

Activations Density 0.111%

names of notable geographical locations, specifically lakes and plazas

No Comments

No Known Activations