INDEX

Explanations

mentions of locations and the context of location-based actions or references

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

fnlp/Llama-Scope-R1-Distill/800M-Slimpajama-0-OpenR1-Math-220k/L15R

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Hzfinfdu/SlimPajama-3B

Features

32,768

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.15

imu

-0.14

ãģ«ãģĹãģ¦

-0.13

 spin

-0.13

inson

-0.13

zal

-0.13

roadcast

-0.13

ARGET

-0.13

INC

-0.12

argas

-0.12

POSITIVE LOGITS

Raises

0.14

ë§¹

0.14

uste

0.14

herits

0.14

owski

0.14

æ·

0.14

ë´ī

0.14

ffset

0.14

poses

0.13

å¤§åħ¨

0.13

Activations Density 0.581%

mentions of locations and the context of location-based actions or references

No Comments

No Known Activations