INDEX

Explanations

mentions of the name "Sandra"

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

Ã¤re

-0.18

obar

-0.15

ahun

-0.15

oss

-0.14

emu

-0.14

setUp

-0.14

 åĽ

-0.14

etu

-0.14

 pareja

-0.14

lij

-0.13

POSITIVE LOGITS

arith

0.15

VR

0.14

Ø°

0.14

 sensit

0.14

unts

0.14

 Walsh

0.14

istan

0.14

oÅ¾

0.14

illon

0.13

attery

0.13

Activations Density 0.002%

mentions of the name "Sandra"

No Comments

No Known Activations