INDEX

Explanations

instances of the word 'access' and its related contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rone

-0.17

 accessed

-0.16

_ACCESS

-0.16

 acces

-0.16

theless

-0.16

 acess

-0.15

AGER

-0.15

ÙĪÙĨØ§

-0.15

 acesso

-0.15

 accesses

-0.15

POSITIVE LOGITS

ibly

0.28

ability

0.26

orial

0.24

ib

0.24

ible

0.23

ibil

0.23

ions

0.22

ibility

0.20

ibel

0.19

 points

0.19

Activations Density 0.015%

instances of the word 'access' and its related contexts

No Comments

No Known Activations