INDEX

Explanations

names of individuals and their associated statistics or records

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

esty

-0.18

anka

-0.16

reed

-0.16

elm

-0.16

aldi

-0.15

oxid

-0.15

OMPI

-0.15

Ð»Ð¾Ð²Ð°

-0.15

ekli

-0.14

cope

-0.14

POSITIVE LOGITS

 Attempt

0.16

Attempt

0.15

 mastur

0.14

é©¾

0.14

ê³ł

0.14

 Header

0.13

 Booking

0.13

JsonValue

0.13

 atas

0.13

Î¹ÎºÎ±

0.13

Activations Density 0.008%

names of individuals and their associated statistics or records

No Comments

No Known Activations