INDEX

Explanations

names of historical figures and their relationships in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ngrx

-0.17

apse

-0.16

æ®

-0.16

luet

-0.15

allel

-0.15

anvas

-0.14

.hw

-0.14

 Brigade

-0.14

hd

-0.14

HR

-0.14

POSITIVE LOGITS

 Ralph

0.18

Roger

0.17

 atte

0.16

 Roger

0.16

Bot

0.15

 meiden

0.15

 Baldwin

0.15

ulf

0.15

 Adam

0.15

acio

0.14

Activations Density 0.028%

names of historical figures and their relationships in a narrative context

No Comments

No Known Activations