INDEX

Explanations

references to specific attributes, features, or characteristics of objects or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

han

-0.17

antro

-0.16

swith

-0.15

peq

-0.14

reflection

-0.14

hani

-0.14

ÑģÐ¾ÑĢ

-0.14

 ãĥı

-0.14

 McInt

-0.14

oman

-0.13

POSITIVE LOGITS

 instead

0.17

0.15

Trace

0.15

 stead

0.15

0.14

 Instead

0.14

ach

0.13

 Kimber

0.13

itech

0.13

Activations Density 0.335%

references to specific attributes, features, or characteristics of objects or entities

No Comments

No Known Activations