INDEX

Explanations

terms related to storytelling elements and narrative structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

nit

-0.17

nt

-0.15

    ↵    ↵

-0.14

(er

-0.13

asso

-0.13

ici

-0.13

string

-0.13

stay

-0.13

istic

-0.13

oggle

-0.13

POSITIVE LOGITS

cies

0.17

CompleteListener

0.17

ously

0.16

entimes

0.16

ãģĬãĤĬ

0.16

-vous

0.15

hip

0.15

ship

0.15

inition

0.15

otros

0.15

Activations Density 3.655%

terms related to storytelling elements and narrative structure

No Comments

No Known Activations