INDEX

Explanations

phrases indicating time-related references

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

reu

-0.15

_legacy

-0.15

enus

-0.15

AMY

-0.15

Ãłm

-0.14

lue

-0.14

 hind

-0.14

bung

-0.14

aca

-0.14

ead

-0.13

POSITIVE LOGITS

elmet

0.14

ëĤľ

0.14

nak

0.14

 ÑĥÐ¼Ð¾Ð²

0.13

Vit

0.13

emon

0.13

 Matth

0.13

 africa

0.13

cken

0.13

ARB

0.13

Activations Density 0.017%

phrases indicating time-related references

No Comments

No Known Activations