INDEX

Explanations

terms related to measurements, statistics, and data analysis

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

ØªØ²

-0.16

chein

-0.16

dif

-0.15

/lg

-0.15

rung

-0.15

zzo

-0.15

ngo

-0.15

rocket

-0.15

æķ£

-0.14

èİ

-0.14

POSITIVE LOGITS

Transition

0.14

transition

0.14

 gate

0.14

 Initiative

0.13

gate

0.13

 transition

0.13

Gate

0.13

 Transition

0.13

_gate

0.13

Activations Density 0.352%

terms related to measurements, statistics, and data analysis

No Comments

No Known Activations