INDEX

Explanations

key terms and titles related to various topics, predominantly in a structured or informational context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

von

-0.15

ãĥ©ãĥ³ãĥī

-0.15

ance

-0.15

éĩı

-0.15

bage

-0.15

TERM

-0.15

_rw

-0.14

assen

-0.14

sworth

-0.14

arken

-0.14

POSITIVE LOGITS

elier

0.15

 Lies

0.14

EGIN

0.14

lek

0.14

&oacute

0.14

anja

0.14

eci

0.14

fe

0.14

 Banc

0.13

enheim

0.13

Activations Density 0.028%

key terms and titles related to various topics, predominantly in a structured or informational context

No Comments

No Known Activations