INDEX

Explanations

specific nouns and significant events or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

irie

-0.15

pNet

-0.15

Ø¯Ùī

-0.14

amt

-0.13

DCF

-0.13

SOLE

-0.13

abbr

-0.13

utter

-0.13

å²³

-0.13

imonial

-0.13

POSITIVE LOGITS

osen

0.15

ewn

0.15

avia

0.15

ABCDEFGHIJKLMNOP

0.15

ï»¿↵↵

0.14

uds

0.14

âĢ¦âĢ¦ãĢĤ

0.14

 ä½į

0.14

iew

0.14

egra

0.14

Activations Density 0.004%

specific nouns and significant events or concepts

No Comments

No Known Activations