INDEX

Explanations

occurrences of numerical values and associated contextual phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

cum

-0.16

oter

-0.15

agger

-0.14

ä¸¾

-0.14

alim

-0.14

fell

-0.14

 getIndex

-0.14

ucz

-0.14

 comp

-0.14

åĶĩ

-0.14

POSITIVE LOGITS

enstein

0.16

Ø§Ø·

0.16

\Carbon

0.15

arter

0.14

æĸĩåŃ¦

0.14

ANJI

0.14

 Trie

0.14

0.13

anzi

0.13

Activations Density 0.002%

occurrences of numerical values and associated contextual phrases

No Comments

No Known Activations