INDEX

Explanations

references to various categorical classifications and settings in technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

alach

-0.16

ORE

-0.16

.dw

-0.16

eli

-0.15

ep

-0.15

oe

-0.14

.dd

-0.14

ording

-0.14

 mant

-0.14

alf

-0.14

POSITIVE LOGITS

hiba

0.16

emonic

0.15

 twice

0.15

0.14

PFN

0.14

æĭĶ

0.14

BFS

0.14

ExecutionContext

0.14

arra

0.13

AbsolutePath

0.13

Activations Density 0.382%

references to various categorical classifications and settings in technical contexts

No Comments

No Known Activations