INDEX

Explanations

phrases involving setting and achieving goals or standards

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

GD

-0.15

åł¡

-0.15

ordan

-0.15

odge

-0.14

duc

-0.14

overy

-0.13

 OPTIONS

-0.13

_Options

-0.13

OutputStream

-0.13

uality

-0.13

POSITIVE LOGITS

 aside

0.19

yah

0.16

lesh

0.16

 Aside

0.16

tle

0.16

env

0.15

icas

0.15

Î¸Î¿ÏĤ

0.15

cut

0.15

hift

0.15

Activations Density 0.062%

phrases involving setting and achieving goals or standards

No Comments

No Known Activations