INDEX

Explanations

phrases indicating intention or desire

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

abyrinth

-0.16

/or

-0.16

hn

-0.16

ucci

-0.16

hest

-0.15

esi

-0.15

(es

-0.15

LETE

-0.15

.Compiler

-0.14

abyrin

-0.14

POSITIVE LOGITS

0.16

ê¶Į

0.15

ed

0.15

ondo

0.15

Zus

0.14

ãĥ³ãĤº

0.14

0.13

Activations Density 0.029%

phrases indicating intention or desire

No Comments

No Known Activations