INDEX

Explanations

references to familial connections and relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

 Inputs

-0.16

ervals

-0.15

isci

-0.15

unic

-0.15

ÑĢÑĥÑĪ

-0.14

icast

-0.14

ampus

-0.14

Î²Î¬Î»

-0.14

iov

-0.14

 inputs

-0.14

POSITIVE LOGITS

lier

0.16

SHIP

0.15

-family

0.15

èŃľ

0.15

 Rosenstein

0.14

ashi

0.14

ellen

0.14

ãĥªãĥ¼

0.14

æĩī

0.14

Activations Density 0.055%

references to familial connections and relationships

No Comments

No Known Activations