INDEX

Explanations

terms related to duration or timeframes, particularly focusing on long-term and near-term references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ÑĤÐ¸Ð½

-0.15

tps

-0.15

VRT

-0.15

_ENGINE

-0.14

RYPTO

-0.14

ils

-0.14

ÌĨ

-0.14

å¯¿

-0.14

 Northwestern

-0.13

rupa

-0.13

POSITIVE LOGITS

uzzer

0.17

ambi

0.17

0.14

æĥħåĨµ

0.14

 unders

0.14

SenderId

0.14

ya

0.14

ourse

0.14

zzo

0.14

yms

0.13

Activations Density 0.089%

terms related to duration or timeframes, particularly focusing on long-term and near-term references

No Comments

No Known Activations