INDEX

Explanations

key names and significant terms related to various subjects, particularly focusing on distinctions and classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ORMAT

-0.16

ãĥ¼ãĥĭ

-0.16

azing

-0.15

utsch

-0.15

-0.14

avage

-0.14

.Guna

-0.14

orno

-0.14

atomic

-0.14

azen

-0.14

POSITIVE LOGITS

ores

0.16

Ã³m

0.15

Geb

0.15

pg

0.15

 felt

0.15

onet

0.14

ilan

0.14

outu

0.14

ì¹

0.14

PG

0.14

Activations Density 0.001%

key names and significant terms related to various subjects, particularly focusing on distinctions and classifications

No Comments

No Known Activations