INDEX

Explanations

iable

np_max-act · gemini-2.0-flash

The neuron activates on the standard hypothesis phrase “continuous on [a,b] and differentiable on (a,b),” flagging statements of continuity‐and‐differentiability over intervals.

oai_token-act-pair · o4-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

 encoding

-0.07

-prefix

-0.07

Duration

-0.06

 Title

-0.06

$c

-0.06

(Const

-0.06

 deadlines

-0.06

 fact

-0.06

_lambda

-0.06

_cost

-0.06

POSITIVE LOGITS

یتی

0.06

ssa

0.06

 Importance

0.06

 forte

0.06

 Основ

0.06

�

0.06

 οποία

0.06

_SCRIPT

0.06

èles

0.06

aison

0.06

Activations Density 0.005%

iable

The neuron activates on the standard hypothesis phrase “continuous on [a,b] and differentiable on (a,b),” flagging statements of continuity‐and‐differentiability over intervals.

No Comments

No Known Activations