INDEX

Explanations

specific characters or symbols used in digital media or text formats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ãĥ«ãĥĪ

-0.18

Ø´Ùĩ

-0.15

anlÄ±

-0.15

ÑģÐ¾

-0.14

ocio

-0.13

osaur

-0.13

 clubhouse

-0.13

 Away

-0.13

cio

-0.13

aggi

-0.13

POSITIVE LOGITS

 cause

0.15

put

0.15

set

0.15

lien

0.15

.hh

0.14

 causes

0.14

ResultsController

0.14

erset

0.14

 left

0.14

arget

0.14

Activations Density 0.009%

specific characters or symbols used in digital media or text formats

No Comments

No Known Activations