INDEX

Explanations

repeated references to "plot" or related terms in the context of film analysis

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

hue

-0.18

ses

-0.15

leet

-0.15

oo

-0.15

oe

-0.14

ovali

-0.14

ilton

-0.14

WD

-0.14

coma

-0.14

hood

-0.14

POSITIVE LOGITS

ting

0.31

ter

0.26

tery

0.19

iful

0.18

TERS

0.17

TER

0.17

anic

0.17

teri

0.17

 Thick

0.16

avicon

0.16

Activations Density 0.009%

repeated references to "plot" or related terms in the context of film analysis

No Comments

No Known Activations