INDEX

Explanations

references to location and movement within a narrative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 today

-0.15

deaux

-0.15

Act

-0.13

conn

-0.13

 subsidi

-0.13

 industri

-0.13

ewear

-0.13

 nationals

-0.13

POSITIVE LOGITS

 bless

0.21

fur

0.20

iv

0.20

 eskort

0.20

 surpr

0.20

 terror

0.19

 kidn

0.19

 persu

0.19

fur

0.18

Fur

0.17

Activations Density 0.027%

references to location and movement within a narrative

No Comments

No Known Activations