INDEX

Explanations

references to a variety of selections or offerings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

.nz

-0.16

olini

-0.15

 Trace

-0.15

#ad

-0.15

uba

-0.14

ubat

-0.14

za

-0.14

ub

-0.14

asha

-0.14

ARAM

-0.14

POSITIVE LOGITS

 Wrath

0.16

 Benchmark

0.15

oser

0.15

0.14

å»

0.14

zahl

0.14

Ø±Ø§ÙĨ

0.14

ÏĥÏĢ

0.13

 Tort

0.13

Vad

0.13

Activations Density 0.015%

references to a variety of selections or offerings

No Comments

No Known Activations