INDEX

Explanations

references to well-known cultural and fictional narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 since

-0.17

ISO

-0.16

 which

-0.16

 Weston

-0.15

is

-0.15

IDL

-0.15

_since

-0.15

 Which

-0.14

ifo

-0.14

POSITIVE LOGITS

-esque

0.26

èĪ¬

0.24

-style

0.24

-type

0.23

-like

0.22

å¼ı

0.21

-era

0.20

type

0.18

 váºŃy

0.17

-Type

0.17

Activations Density 0.119%

references to well-known cultural and fictional narratives

No Comments

No Known Activations