INDEX

Explanations

ingredient measurements and cooking instructions related to seasoning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

èĪī

-0.16

Î±Îº

-0.16

onde

-0.15

Âª

-0.15

_singleton

-0.14

 neust

-0.14

unkt

-0.14

HEET

-0.14

oola

-0.14

odesk

-0.13

POSITIVE LOGITS

 pepper

0.40

 Pepper

0.35

 salt

0.27

salt

0.26

 black

0.25

Salt

0.25

 Salt

0.24

 ground

0.23

 season

0.23

 Piper

0.23

Activations Density 0.047%

ingredient measurements and cooking instructions related to seasoning

No Comments

No Known Activations