INDEX

Explanations

dialogues and interactions among characters

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

otel

-0.15

Poh

-0.13

ymes

-0.13

Å¾en

-0.13

 Variant

-0.13

 nearly

-0.13

 Pharmacy

-0.13

 Valk

-0.13

ÑĪÐµ

-0.13

ply

-0.13

POSITIVE LOGITS

erson

0.16

APH

0.15

DCALL

0.15

rand

0.15

icht

0.15

mal

0.14

ãĥ©ãĤ¹

0.14

acid

0.14

ikal

0.14

ichni

0.14

Activations Density 0.301%

dialogues and interactions among characters

No Comments

No Known Activations

dialogues and interactions among characters

No Comments

No Known Activations