INDEX

Explanations

specific technical and operational terms related to programming and system functionality

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

mentioned

-0.16

gui

-0.15

civ

-0.15

bx

-0.15

 mentioned

-0.15

 tint

-0.15

 Banc

-0.14

oren

-0.14

infer

-0.13

Ð»ÐµÐ¶

-0.13

POSITIVE LOGITS

emek

0.18

æĻ´

0.16

_elim

0.15

DataStream

0.15

Elim

0.15

_barrier

0.14

 stump

0.14

 AndAlso

0.14

éł

0.14

Activations Density 0.251%

specific technical and operational terms related to programming and system functionality

No Comments

No Known Activations