INDEX

Explanations

descriptions and attributes that indicate clarity and detail in information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ello

-0.17

emi

-0.15

eros

-0.15

uels

-0.15

stad

-0.15

OMIC

-0.15

ential

-0.15

clair

-0.14

iros

-0.14

ÃĹ↵↵

-0.14

POSITIVE LOGITS

-cut

0.26

ances

0.21

-eyed

0.20

 rÃłng

0.20

mente

0.19

cut

0.19

ness

0.19

zeitig

0.18

ened

0.18

headed

0.17

Activations Density 0.042%

descriptions and attributes that indicate clarity and detail in information

No Comments

No Known Activations