INDEX

Explanations

descriptors that indicate similarity or likeness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

roy

-0.15

_IOCTL

-0.14

nist

-0.13

minor

-0.13

OCR

-0.13

ÑİÑĢ

-0.13

 Taken

-0.13

loa

-0.13

çģ½

-0.13

POSITIVE LOGITS

-like

0.20

ä¸ľè¥¿

0.19

 qualities

0.17

qualities

0.16

 proportions

0.16

ily

0.16

 behaviour

0.16

sian

0.15

kova

0.15

ettel

0.15

Activations Density 0.044%

descriptors that indicate similarity or likeness

No Comments

No Known Activations