INDEX

Explanations

references to data structure identifiers and their relations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ridor

-0.18

 Boulder

-0.16

cco

-0.16

 Grove

-0.15

aggi

-0.15

quete

-0.15

peer

-0.14

ħ

-0.14

ynn

-0.14

ysis

-0.14

POSITIVE LOGITS

ABC

0.34

0.27

abc

0.26

ABC

0.25

DEF

0.24

0.23

_ABC

0.23

Activations Density 0.075%

references to data structure identifiers and their relations

No Comments

No Known Activations