INDEX

Explanations

references to time, particularly focusing on durations and specific time frames

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

elli

-0.15

ãĥ«ãĥī

-0.14

oulos

-0.14

ir

-0.14

leck

-0.13

 somehow

-0.13

chs

-0.13

çĳ

-0.13

POSITIVE LOGITS

//{{

0.14

enaire

0.14

å½¹

0.14

allis

0.14

wrap

0.13

imes

0.13

-sort

0.13

apist

0.13

leston

0.13

axon

0.13

Activations Density 0.053%

references to time, particularly focusing on durations and specific time frames

No Comments

No Known Activations