INDEX

Explanations

common connector words and phrases that establish continuity and context in discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

_Execute

-0.17

iled

-0.16

é¤Ĭ

-0.15

rani

-0.15

 Hass

-0.15

ãĥ¥

-0.14

ileo

-0.14

til

-0.14

 Gill

-0.14

noh

-0.14

POSITIVE LOGITS

ken

0.16

-valu

0.15

ostat

0.15

allest

0.14

iso

0.14

atty

0.14

Nat

0.14

.cgi

0.14

aws

0.14

onom

0.14

Activations Density 0.001%

common connector words and phrases that establish continuity and context in discussions

No Comments

No Known Activations