INDEX

Explanations

e

np_max-act · gemini-2.0-flash

technical terminology and code-related constructs in programming contexts.

oai_token-act-pair · gpt-4o-mini Triggered by @xinyanhu8

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

FIELD

-0.06

αιο

-0.06

 Booth

-0.06

裂

-0.06

[maxn

-0.06

Crop

-0.06

Å

-0.06

_Free

-0.06

んな

-0.06

 voluntary

-0.06

POSITIVE LOGITS

 downhill

0.07

.slide

0.07

ew

0.07

 ActionController

0.07

	anim

0.07

uw

0.06

	dialog

0.06

odash

0.06

	HANDLE

0.06

 overseeing

0.06

Activations Density 0.001%

e

technical terminology and code-related constructs in programming contexts.

No Comments

No Known Activations

e

technical terminology and code-related constructs in programming contexts.

No Comments

No Known Activations