INDEX

Explanations

specific numerical data or values, particularly related to comparisons or lists

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

opak

-0.15

sim

-0.14

Mu

-0.14

 focal

-0.14

relation

-0.14

embre

-0.14

Env

-0.14

 local

-0.14

ija

-0.13

Tee

-0.13

POSITIVE LOGITS

aghan

0.16

ãĥĥãĤ«ãĥ¼

0.16

celik

0.16

outh

0.15

RLF

0.15

isen

0.15

ÑĥÐ»Ñİ

0.15

orte

0.15

ittings

0.14

geist

0.14

Activations Density 0.009%

specific numerical data or values, particularly related to comparisons or lists

No Comments

No Known Activations