INDEX

Explanations

references to specific names or titles, particularly those associated with people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

NotSupportedException

-0.19

_userdata

-0.16

 Rencontre

-0.16

alia

-0.15

å¯¸

-0.15

ivant

-0.15

pton

-0.15

 å¾

-0.15

Prompt

-0.14

rams

-0.14

POSITIVE LOGITS

ammen

0.15

erve

0.15

 Lester

0.15

 Linden

0.15

lur

0.14

_RESERVED

0.14

gorith

0.14

ounge

0.14

 tall

0.14

ype

0.13

Activations Density 0.011%

references to specific names or titles, particularly those associated with people

No Comments

No Known Activations